Intelligence Architect (Forward-Deployed AI Engineer)

AI Architect – Enterprise AI & Generative AI ( Remote) - Contractual

Experience: 8+ years

Location: Remote, India

Employment Type: Contractual

Working Hours: 3:00 PM – 12:00 AM IST

Client Engagement: US-based client

About the Role

We are looking for a hands-on, client-facing AI Architect to lead the architecture, technical direction, and production implementation of enterprise AI and Generative AI solutions for a US-based client.

You should combine strong software engineering and cloud architecture fundamentals with practical experience building secure, scalable, and reliable AI applications. This role involves end-to-end technical ownership, from solution design and prototyping to production deployment and optimization. It is not a research-only, advisory-only, or prompt-writing position.

Key Responsibilities

• Lead end-to-end architecture and delivery of AI/ML and Generative AI solutions, from discovery and proof of concept to production rollout.
• Design LLM-powered applications using Retrieval-Augmented Generation (RAG), embeddings, vector databases, AI agents, and orchestration frameworks.
• Define data ingestion, chunking, retrieval, grounding, evaluation, and knowledge-refresh strategies.
• Select appropriate AI models and platforms based on quality, latency, cost, security, and operational requirements.
• Design cloud-native architectures, APIs, integrations, identity controls, monitoring, and resilient deployment patterns.
• Create architecture diagrams, technical designs, implementation roadmaps, and technical standards.
• Implement AI quality and safety measures, including hallucination mitigation, guardrails, access controls, and prompt-injection defenses.
• Guide engineering, data, ML, and DevOps teams through implementation, code reviews, troubleshooting, and go-live readiness.
• Lead technical discussions and design reviews with US client stakeholders.
• Establish production monitoring, CI/CD, versioning, incident handling, and performance and cost optimization practices.

Required Skills & Qualifications

• 8+ years of relevant experience in software engineering, AI/ML engineering, data engineering, or technology architecture.
• Proven experience personally architecting and deploying at least one enterprise-grade AI or Generative AI solution into production.
• Strong practical knowledge of LLMs, RAG, embeddings, vector databases, orchestration frameworks, and model evaluation.
• Hands-on experience with Python and APIs, including prototyping, code review, and troubleshooting.
• Experience with at least one major cloud platform: Microsoft Azure, AWS, or Google Cloud Platform (GCP).
• Understanding of data pipelines, SQL/NoSQL databases, containers, CI/CD, MLOps, and LLMOps.
• Knowledge of enterprise security, privacy, identity and access management, and responsible AI practices.
• Experience independently leading architecture workshops, design reviews, and technical discussions with US clients.
• Excellent written and spoken English, documentation, and stakeholder management skills.
• Availability to work from 3:00 PM to 12:00 AM IST and willingness to accept a contractual engagement.

Preferred Experience

• Azure AI Foundry, Azure OpenAI, Amazon Bedrock, or Google Vertex AI.
• Azure AI Search or equivalent retrieval tools.
• LangChain, LangGraph, Semantic Kernel, and agent/tool orchestration.
• Model fine-tuning, predictive ML, document intelligence, multimodal AI, or real-time AI applications.
• Experience in cloud modernization, enterprise integrations, data analytics, or technology consulting.
• Relevant AI/cloud architecture certifications and experience mentoring technical teams.

What Success Looks Like

• Designing secure, scalable, production-ready AI solutions rather than demos or conceptual presentations.
• Making sound technical decisions around feasibility, performance, reliability, cost, and AI risks.
• Taking ownership of architecture decisions and resolving technical blockers with limited supervision.
• Building trust with senior US stakeholders and collaborating effectively with India-based delivery teams.

Contract Details

• Initial engagement: Minimum 3 months, with extension subject to project requirements and performance.
• Working schedule: 3:00 PM – 12:00 AM IST.
• Potential permanent employment: After 18 months, the client may consider direct permanent employment at its sole discretion. Conversion is not guaranteed.

Mandatory Screening Criteria

Candidates should be able to:

• Explain an enterprise AI/GenAI solution they personally architected and deployed, including architecture, scale, evaluation, and business impact.
• Whiteboard an enterprise RAG or agentic solution covering data flow, security, authentication, authorization, monitoring, and cost controls.
• Discuss real-world model-quality issues, hallucinations, privacy risks, incidents, and architectural trade-offs.
• Lead a technical design review with US client stakeholders.
• Confirm acceptance of the working hours and contractual engagement.

Apply only if you have hands-on experience architecting and deploying enterprise AI/GenAI solutions in production.

About the Role

We are a 25-year-old company building toward a technology-centered workforce where AI agents and automation handle more of the day-to-day work, supported by people with specialized expertise.

We are automating our existing workflows, expanding our use of agentic AI, launching a sister company next year, and building a fleet of Hermes AI agents to delegate and manage work.

We are looking for a hands-on AI Systems Architect & Company Technology Lead to help build, connect, and continuously improve these systems.

Key Responsibilities

·       Own and improve our Microsoft 365 technology environment and AI-powered workflows.

·       Build automations connecting email, meetings, Planner, and other business systems.

·       Research, test, implement, and maintain AI tools and integrations.

·       Build and manage the Hermes agent fleet, including shared memory, delegation rules, workflows, and reporting.

·       Connect AI agents to business systems and SaaS platforms using APIs, webhooks, databases, and automation tools.

·       Help build an internal agentic marketing department by selecting and connecting the right AI tools.

·       Continuously troubleshoot, improve, and document our technology systems.

·       Help apply these systems as the company expands into new ventures.

Must-Haves

·       Strong technical problem-solving and self-teaching ability.

·       Solid hands-on experience building, configuring, and managing AI agents.

·       Experience connecting AI agents and multiple SaaS platforms using APIs, webhooks, databases, and automation tools.

·       Comfortable with Python, JavaScript, or similar.

·       Ability to independently research, build, test, troubleshoot, and improve systems.

·       Strong interest in AI, automation, and emerging technology.

This is a rapidly changing field therefore Direct experience working with actual Hermes agents is not required. However, hands-on experience working with AI agents is required.

What we need is someone who already understands the fundamentals of deploying AI agents, giving them instructions and tools, connecting them to other systems, and making them work reliably in a real business environment.

The Opportunity

This is an opportunity to help us discover and implement what is actually possible with AI today, and to lead the process of expanding workflows along with the rapidly advancing capabilities — this role is not only to implement a technology that has already been figured out.

Role Overview 

We are looking for an AI Engineer to design, build, and ship production AI systems, including agentic AI applications, for enterprise clients. This is a hands-on engineering role: you will write production code, build and evaluate models and agents, and work closely with architects and product teams to take solutions from prototype to scale. 

Key Responsibilities 

Design and build agentic AI systems: agent workflows, tool/function-calling, memory, and human-in-the-loop patterns. Build and productionise RAG pipelines, prompt-based applications, and LLM integrations across providers. Develop and maintain data and ML pipelines: feature engineering, model training, evaluation, and monitoring. Integrate AI systems with enterprise applications (CRMs, ERPs, ITSM tools) via APIs, events, and MCP-based tool servers. Implement guardrails, prompt-injection defences, and evaluation frameworks to keep AI systems safe and reliable in production. 

Write clean, tested, production-grade code and participate actively in code and design reviews. 

Collaborate with architects, product managers, and delivery teams to translate requirements into working AI solutions. Troubleshoot and optimise AI systems for accuracy, latency, and cost in production. 

Required Qualifications 

8–12 years of hands-on software engineering experience, with a strong, unbroken technical track record. Hands-on experience building and shipping AI/ML systems in production, not just POCs. 

Practical experience with agentic AI systems and at least one major agent framework (LangGraph, CrewAI, AutoGen, OpenAI Agents SDK, Bedrock Agents/Strands, or Semantic Kernel). 

Experience with LLM/GenAI systems: RAG pipelines, prompt engineering, structured outputs, and tool calling across providers. 

Strong Python skills (TypeScript/Node.js a plus), with production-grade testing, CI/CD, and API design practices. Working knowledge of ML fundamentals: model evaluation, feature engineering, and experimentation. Cloud-native experience on AWS and/or Azure: containers, serverless, event backbones, and vector databases. Understanding of LLM safety and reliability practices: guardrails, prompt-injection defences, and observability. 

Read This Before Anything Else

We have 6 developers who can ship. What we don't have is someone who turns that into a real engineering function: real architecture, real leverage, real AI-driven advantage. If that gap sounds like an opportunity rather than a headache, you're in the right place. If it sounds like a lot of undefined work with no playbook handed to you, this one probably isn't for you. That's completely okay. There are plenty of great roles that fit differently.

About CraftMyPlate

CraftMyPlate is Hyderabad's go-to platform for food experiences for micro-events: house parties, birthdays, office celebrations, festive gatherings, and more. We're building the operating system for how India discovers, customises, and orders food for smaller events. We're backed by established founders and investors, and we're funded and growing fast. The next phase of that growth runs through engineering.

Where We Stand

Some numbers, because they matter more than adjectives. Order volume has grown 50x in two years, and we're compounding at roughly 3x year over year, without giving up equity to fund it. That means the business runs on its own economics. The growth is real demand, not runway bought with dilution, and every efficient architectural decision this role makes directly protects that.

Most people size up an opportunity by asking what's going to change in ten years. The more useful question, and the one this company is built around, is what won't change. People will keep gathering. They'll keep celebrating, hosting, and marking festivals, in 10 years and in 20. That permanence is the bet. You're not building infrastructure for a trend cycle. You're building for a category that outlasts the current AI wave, the next funding round, and probably us too.

The Technical Reality

Here's an honest read of the engineering problem, not a sanitized version of it.

Event-driven commerce doesn't scale like typical e-commerce. Demand isn't smooth, it's spiky: weekends, festival calendars, and event dates create real load concentration, and each order is tied to a hard deadline that can't slip the way a shipped package can. That has direct architectural consequences: systems need to handle bursty, unpredictable traffic without paying for idle capacity the rest of the time, which is exactly why we're serverless-first on AWS rather than running a fixed fleet sized for peak.

Underneath that, every order touches multiple systems that have to stay consistent: kitchen and vendor fulfillment status, inventory across partners, payment gateway settlement, and refunds, often in real time and often across more than one vendor for a single event. Getting that consistency right across SQL and NoSQL stores, without it becoming a source of support tickets and manual reconciliation, is a real architecture problem, not a CRUD problem.

The AI-agent layer is the next lever, and it's a business lever as much as a technical one. Every workflow we can hand to a well-orchestrated agent instead of a new hire is a workflow that scales without adding headcount, which is exactly how a company grows 3x a year without diluting equity to fund the team behind it. That's why agent orchestration across multiple LLMs, using LangGraph, sits in the "go deep" tier of this role rather than being a nice-to-have.

You'll likely find some of this framing right and some of it worth challenging once you're actually in the codebase. That's expected, and honestly preferred over someone who just nods along.

Why This Role Exists

You'll be the most senior technical person in the company, reporting directly to the founder. Not a manager brought in to run standups. An owner. You set the architecture, you write code yourself, and you make the team materially better. You also own where AI and automation take this company next, starting with our first in-house AI agent product (details shared in the interview), and expanding from there into how the company runs, department by department: HR, finance, marketing, design, development, all sitting on an engineering layer that you design.

If you've outgrown a role where you plan but don't build, or where good ideas die in a committee, this is built to be the opposite of that.

What You'll Own

• Architecture, end to end. Scalable, cost-efficient systems from day one, not "fix it later" engineering. You own the decisions and their long-term consequences.
• Hands-on building. You are still writing code and shipping. This isn't a seat where you review other people's work all day. You lead by building.
• The engineering team. Directly manage, mentor, and level up our 6 developers. Build the technical bar, the review culture, and the calibration that lets the team ship independently.
• The AI-agent roadmap. Own the architecture behind our first AI agent product, then the broader strategy for AI agents and automation across every function in the company, with engineering as the layer underneath all of it.
• Team scaling. Build the next layer of leads under you so execution quality scales without you being the bottleneck.
• Technical accountability. When something breaks, you fix it. You don't escalate and wait.

Our Stack, and the Depth We Expect

Not everything on this list needs the same level of mastery. Some of it you need to own at an architectural level. The rest you need to be strong enough to build yourself, direct the team on, or delegate to AI agents with confidence.

Go deep here. This is where the real architecture decisions live, and where the business impact is highest:

• AWS, serverless first. You should be genuinely well versed in AWS application development, not just "have used AWS." You should be able to design and guide serverless architecture (Lambda, API Gateway, DynamoDB, Step Functions, and similar) as our default way of building, because our demand curve is spiky by nature and fixed infrastructure is money left on the table.
• TypeScript, our primary language across backend and frontend.
• Agent orchestration across multiple LLMs, using LangGraph. This is core to our AI roadmap and our path to scaling operations without scaling headcount. You own how it's architected, not just how it's used.

Working proficiency. Build it yourself, direct the team, or hand it to an AI agent and know if the output is right.

This Is You If

• You've built and shipped real production systems yourself, not just reviewed other people's architecture from a distance.
• You go deep wherever the problem is, and you're comfortable owning the exact stack described above, not just "full-stack" in the abstract.
• You've made engineers around you measurably better, whether or not you've held the title for it yet.
• You're already using AI coding tools and agents seriously, like Claude, Cursor, or similar tools, as part of how you build, not as something you tried once. We'll likely explore this together in the interview.
• You have a bias toward leverage over hours. You'd rather automate or systematize a problem than grind through it. But when something's live and needs to be done right, you see it through completely, with no half-finished work.
• You want to build something for years, not land somewhere comfortable. We'll know the difference from how you talk about your last three years.

This Might Not Be the Right Fit If

• You'd prefer a stable, well-defined role with clear boundaries and someone else making the calls. That's a fair thing to want, just not what this is.
• You'd rather receive direction than bring us architecture and AI strategy yourself.
• You haven't yet gotten hands-on with AI coding tools in your daily work.
• You're drawn more to the title than the work behind it.

If none of that sounds like you, we'd love to hear from you.

Requirements

• 5 to 7 years of experience in software engineering, with real ownership of architecture-level decisions, not just feature delivery.
• Prior experience leading or mentoring engineers, formally or informally.
• Tier-1 or Tier-1+ engineering college strongly preferred (IIT, BITS, top NIT tier, or equivalent). We'll consider other institutions only with clearly commendable, verifiable work: real systems you can walk us through in depth, strong open-source contributions, or a track record that speaks for itself. Pedigree is a proxy for speed, not a checkbox. We test for the underlying ability regardless.
• Comfortable in an early-stage environment: undefined problems, few processes, and the expectation that you help define both.

Compensation

Competitive, with equity. We're formalizing a structured ESOP program alongside this hire. Specific numbers are discussed directly in later interview rounds.

If reading this got you a little excited about what you'd build here, we'd genuinely love to talk. If it didn't quite land, no hard feelings. We just want the right fit for both sides.

About the Role

We are seeking a hands-on Tech Lead to design, build, and integrate AI-driven systems that automate and enhance real-world business workflows. This is a high-impact role for someone who enjoys full-stack ownership — from backend AI architecture to frontend user experiences — and can align engineering decisions with measurable product outcomes.

You will begin as a strong individual contributor, independently architecting and deploying AI-powered solutions. As the product portfolio scales, you will lead a distributed team across India and Australia, acting as a System Integrator to align engineering, data, and AI contributions into cohesive production systems.

Example Project

Design and deploy a multi-agent AI system to automate critical stages of a company’s sales cycle, including:

• Generating client proposals using historical SharePoint data and CRM insights
• Summarizing meeting transcripts
• Drafting follow-up communications
• Feeding structured insights into dashboards and workflow tools

The solution will combine RAG pipelines, LLM reasoning, and React-based interfaces to deliver measurable productivity gains.

Key Responsibilities

• Architect and implement AI workflows using LLMs, vector databases, and automation frameworks
• Act as a System Integrator, coordinating deliverables across distributed engineering and AI teams
• Develop frontend interfaces using React/JavaScript to enable seamless human-AI collaboration
• Design APIs and microservices integrating AI systems with enterprise platforms (SharePoint, Teams, Databricks, Azure)
• Drive architecture decisions balancing scalability, performance, and security
• Collaborate with product managers, clients, and data teams to translate business use cases into production-ready systems
• Mentor junior engineers and evolve into a broader leadership role as the team grows

Ideal Candidate Profile

Experience Requirements

• 5+ years in full-stack development (Python backend + React/JavaScript frontend)
• Strong experience in API and microservice integration
• 2+ years leading technical teams and coordinating distributed engineering efforts
• 1+ year of hands-on AI project experience (LLMs, Transformers, LangChain, OpenAI/Azure AI frameworks)
• Prior experience in B2B SaaS environments, particularly in AI, automation, or enterprise productivity solutions

Technical Expertise

• Designing and implementing AI workflows including RAG pipelines, vector databases, and prompt orchestration
• Ensuring backend and AI systems are scalable, reliable, observable, and secure
• Familiarity with enterprise integrations (SharePoint, Teams, Databricks, Azure)
• Experience building production-grade AI systems within enterprise SaaS ecosystems

Job Title: Full Stack AI Engineer

Location: Remote/Hyderabad

Experience Level: 3-5

Salary Range: 12-18LPA

Application Link:https://beyond.ciltriq.com/apply/BUILD

Description:

Join a team building AI-powered systems that solve complex business problems and automate operational workflows across document processing, voice agents, enterprise integrations, workflow automation, and multi-agent systems.

Strong full-stack foundations: frontend state management, asynchronous user experiences and performance; backend API design, authentication, data modelling, databases, queues and distributed systems.

Strong coding ability in Python and JavaScript or TypeScript, with practical experience in modern frontend frameworks and backend services.

Requirements:

- Design and build complete systems: frontend applications, backend services, APIs, databases, data pipelines and integrations with customer systems.

- Build multi-agent workflows with clear agent responsibilities, tool access, shared state, context management, routing, handoffs and coordination across sequential and parallel tasks.

- Make agent execution dependable through durable state, checkpoints, retries, timeouts, idempotency, recovery and human approval or review where needed.

- Deliver document-processing pipelines, voice agents and retrieval-based AI applications, connecting model outputs to useful actions in real business workflows.

- Own quality in production: automated tests, AI evaluations, guardrails, observability, access controls, deployments, incident response and clear documentation.

- Choose where AI adds value and where deterministic software is the better fit. Balance accuracy, latency, cost, security and maintainability.

- Improve reusable engineering foundations, review code and help other engineers grow as the team expands.

- A solid understanding of tool calling, structured outputs, retrieval, context and memory management, model selection and evaluation.

- Practical cloud and deployment experience, including containers, CI/CD, secrets management, logging, monitoring and production debugging.

- Ability to reason from first principles, investigate failures across system boundaries and communicate technical decisions clearly to customers and teammates.

- Useful additional experience: Document AI and OCR, real-time voice systems, enterprise integrations, agent protocols such as MCP, and orchestration frameworks.

- Useful additional experience: Mentoring engineers or building reusable platforms.

Position Overview

We are seeking a versatile Senior Full Stack & AI Agent Developer to architect, build, and

maintain end-to-end software solutions spanning web platforms, desktop applications, and

autonomous AI agents capable of interacting with and controlling these software systems.

The ideal candidate will bridge traditional engineering software with cutting-edge artificial

intelligence to automate data processing and enhance operational decision-making. While

not strictly required, a background or strong interest in the energy sector—specifically

drilling and completion operations—is highly desirable.

Key Responsibilities

• Full Stack Development: Design, develop, and deploy robust web applications and

native desktop software utilized by engineering and operational teams.

• AI Agent Engineering: Build, train, and integrate autonomous AI agents and LLM-

driven workflows capable of interpreting data, executing commands, and safely

controlling desktop and web-based software.

• Workflow Automation: Translate complex workflows into intuitive software features

and autonomous agent actions, minimizing manual data entry and operational

bottlenecks.

• Data Integration: Handle high-frequency data streams and integrate them seamlessly

into user interfaces and backend AI models.

• Architecture & Scalability: Ensure high performance, security, and scalability across

cloud infrastructure (AWS/Azure), local desktop environments, and potential edge

computing setups.

• Cross-Functional Collaboration: Work closely with domain experts and end-users to

translate field challenges into technical product requirements.

Required Qualifications & Experience

• Experience: Minimum of 5 years of professional software development experience,

with a proven track record of delivering production-ready web and desktop

applications.

• Programming Languages: Strong proficiency in Python, JavaScript/TypeScript, and at

least one compiled language (C#, C++, or Java).• Web & Desktop Frameworks: Hands-on experience with modern frontend

frameworks (React, Angular, or Vue.js), Node.js, and desktop application development

(Electron, WPF, Qt, or Tauri).

• AI & Agent Tooling: Demonstrated experience building AI agents using LLM APIs

(OpenAI, Anthropic), open-source models (Hugging Face), LangChain, LlamaIndex,

AutoGPT, or custom agent architectures.

• Automation & UI Control: Expertise in software control mechanisms using tools like

Selenium, Playwright, PyAutoGUI, Appium, or computer vision-based GUI automation to

allow AI agents to navigate software.

• Cloud, DevOps & Databases: Experience with Git, Docker, CI/CD pipelines, cloud

platforms (AWS/Azure/GCP), RESTful APIs, GraphQL, and relational/NoSQL databases.

Preferred Qualifications (Strong Plus)

• Industry Domain Expertise: Prior hands-on development experience within the oil and

gas sector, specifically focused on drilling, completions, rig operations, or subsurface

engineering software.

• Data & Protocols: Familiarity with oilfield data standards (e.g., WITSML, OPC-UA) and

time-series databases.

• Experience deploying AI models and agents in edge or low-connectivity environments

(such as offshore rigs or remote drilling sites).

• Familiarity with safety-critical software design and cybersecurity standards in

industrial control systems (ICS/SCADA).

• Degree in Computer Science, Software Engineering, Petroleum Engineering, or a related technical discipline.

Forward-deployed engineers (FDEs) are Mactores' services layer. You embed with the customer's team, own outcomes from discovery through the production cutover, and personally carry the delivery commitment.

The agent platform we deploy absorbs 60–70% of engagement work, discovery, assessment, design, and testing. You absorb the judgment: target architecture, refactoring trade-offs, model selection, cutover strategy, and the decisions an agent platform cannot make. The agent absorbs scale. You absorb judgment. 

This is not a staff-augmentation seat and not an advisory role. You ship.

What you will do?

• Deliver production agentic AI systems and AWS modernization engagements on committed dates across three pillars: Data Platform Modernization, Application & Database Modernization, and AI Agents for Apps.
• Build and productionize AI agents, orchestration, retrieval pipelines, evaluation harnesses, observability running against real customer data, not demo data.
• Convert existing products into agents: expose product functionality as callable tools for agent-to-agent composition, or replace form-and-click UX with agent-native, intent-driven interfaces.
• Convert existing Business processes into agents: expose process functionality as callable tools for agent-to-agent composition, or replace form-and-click UX with agent-native, intent-driven interfaces.
• Embed directly with customer engineering teams. Run architecture sessions, defend design decisions, and align stakeholders from VP Engineering to CTO.
• Make agent decisions traceable and defensible, validation runs in parallel with live workloads, and outputs hold up to internal audit and regulators (HIPAA, PCI-DSS, FSI-grade governance where the vertical demands it).
• Feed field experience back into the platform and practice: your deployment patterns, integration playbooks, and edge cases shape how we deliver.

What are we looking for?

• Excellent communication skills (English) — verbal and written. Non-negotiable. You will present architecture to customer CTOs, write documents that hold up in audit, and defend judgment calls in the room. If you can build but not explain, this role is not a fit.
• You have shipped production agentic AI systems on AWS. Not POCs, not notebooks — systems running in production for real users. This is the primary qualification. Be prepared to walk through what you shipped, the decisions you made, and what broke.
• Deep understanding of agentic architecture — you can design an agent system from first principles and explain why each component exists:
• Agent design patterns: single-agent vs. multi-agent systems, supervisor/orchestrator patterns, hierarchical agent topologies, planner–executor separation, and when each applies.
• Orchestration: building and operating orchestrator agents that decompose tasks, route work to specialist agents or tools, and manage state across multi-step workflows (LangGraph, Strands Agents, CrewAI, or equivalent).
• Memory: short-term/working memory (context management, conversation state) and long-term memory (episodic and semantic stores, vector- and graph-backed retrieval), and the production trade-offs of each.
• Reflection and self-correction: critique loops, self-evaluation, retry-with-feedback patterns, and evaluation harnesses that catch agent failures before customers do.
• Tool use and function calling: schema design, tool-selection reliability, error handling, and agent-to-agent composition.
• RAG and retrieval pipelines: chunking, embedding, hybrid retrieval, reranking, and grounding agent decisions in customer data.
• Strong AWS production experience: Amazon Bedrock and AWS AI services, plus core platform services (Lambda, API Gateway, DynamoDB, RDS/Aurora, Glue, EMR, Redshift, Kinesis, or similar depending on specialization).
• Solid software engineering fundamentals Python, TypeScript, CI/CD, infrastructure-as-code, testing-driven development discipline.
• Experience with data or application modernization (database migration, legacy refactoring, data platform builds) is a strong plus, since agents run against these workloads.
• Indicative experience: roughly 3–10 years in engineering roles, with agentic AI / GenAI as your current day job. We have demonstrated agent-native expertise over tenure — an engineer with 3–4 years of hands-on agentic AI work typically outperforms a 12-year generalist on this work.

You'll be preferred if you've:

• US English verbal and written fluency 
• Delivery experience in one or more of our verticals: Financial Services, Healthcare & Life Sciences, Internet & Software, Manufacturing, or Telco/Media/Entertainment/Gaming/Sports.
• Model tuning and fine-tuning: systematic prompt engineering and optimization; parameter-efficient fine-tuning (LoRA/QLoRA or similar); instruction tuning; working knowledge of RLHF/DPO; sound judgment on when to fine-tune vs. prompt vs. RAG; and evaluation of tuned models against baselines. Fine-tuning experience on Amazon Bedrock or SageMaker is a plus.
• Experience with compliance-sensitive AI systems (HIPAA, PCI-DSS, SOC 2, data residency).
• Knowledge graph, code-analysis (AST), or CDC/streaming experience (Debezium, Kafka/MSK).
• Solid software engineering fundamentals — Java, C++, Go Lang, .Net, Rust
• Prior customer-facing consulting or forward-deployed experience.
• AWS certifications (Solutions Architect Professional, Machine Learning Specialty, or Data Analytics).

Why This Role?

• You own outcomes, not tickets. FDEs carry the delivery commitment personally — architecture, judgment, and cutover are yours.
• You work agent-native from day one. Our delivery model would not function without agents. You build with the platform, not around it.
• You ship. Engagements measured in weeks to production, legacy retired, outcomes named. No archived pilots.
• You compound. Field delivery informs the Aedeon platform roadmap; the platform's growth expands what you can deliver. Few engineering roles sit in that loop.

Job Title: AI Architecture Intern

Company: PGAGI Consultancy Pvt. Ltd.

Location: Remote

Employment Type: Internship

Position Overview

We're at the forefront of creating advanced AI systems, from fully autonomous agents that provide intelligent customer interaction to data analysis tools that offer insightful business solutions. We are seeking enthusiastic interns who are passionate about AI and ready to tackle real-world problems using the latest technologies.

Duration: 6 months

Key Responsibilities:

• AI System Architecture Design: Collaborate with the technical team to design robust, scalable, and high-performance AI system architectures aligned with client requirements.
• Client-Focused Solutions: Analyze and interpret client needs to ensure architectural solutions meet expectations while introducing innovation and efficiency.
• Methodology Development: Assist in the formulation and implementation of best practices, methodologies, and frameworks for sustainable AI system development.
• Technology Stack Selection: Support the evaluation and selection of appropriate tools, technologies, and frameworks tailored to project objectives and future scalability.
• Team Collaboration & Learning: Work alongside experienced AI professionals, contributing to projects while enhancing your knowledge through hands-on involvement.

Requirements:

• Strong understanding of AI concepts, machine learning algorithms, and data structures.
• Familiarity with AI development frameworks (e.g., TensorFlow, PyTorch, Keras).
• Proficiency in programming languages such as Python, Java, or C++.
• Demonstrated interest in system architecture, design thinking, and scalable solutions.
• Up-to-date knowledge of AI trends, tools, and technologies.
• Ability to work independently and collaboratively in a remote team environment

Perks:

- Hands-on experience with real AI projects.

- Mentoring from industry experts.

- A collaborative, innovative and flexible work environment

Compensation:

- Stipend: Base is INR 8000/- & can increase up to 20000/- depending upon performance matrix.

After completion of the internship period, there is a chance to get a full-time opportunity as an AI/ML engineer.

Preferred Experience:

• Prior experience in roles such as AI Solution Architect, ML Architect, Data Science Architect, or AI/ML intern.
• Exposure to AI-driven startups or fast-paced technology environments.
• Proven ability to operate in dynamic roles requiring agility, adaptability, and initiative.

About the role

We are building AI systems that read, understand and act on real business documents, bank statements, financial reports, policy documents and forms and putting them into production where accuracy and cost both matters.

This is not a research role and it is not a prompt-writing role. You will own features end to end: pick and deploy open-source models, build the pipelines around them, measure whether they actually work on our documents, drive the cost per document down, and keep the whole thing running in production.

You will work closely with the engineering and product teams, and your work will be directly used by business users from day one.

What you will do

Deploy and evaluate open-source models

• Select, deploy and benchmark open-source LLMs and vision-language models for specific, narrow use cases not general chat.
• Build evaluation sets from real documents and define what "good" means numerically (field-level accuracy, extraction recall, hallucination rate) before shipping.
• Run structured comparisons between models and approaches, and write up the trade-offs so the team can make a decision.
• Apply quantization, batching and other optimizations to fit models into a sensible GPU budget.

Build and optimize AI orchestration

• Design multi-step pipelines that combine deterministic code, ML models and LLM calls and know when not to use an LLM.
• Optimize for latency, cost and reliability: caching, batching, request routing, fallback tiers, retries and graceful degradation.
• Instrument pipelines so failures are visible and traceable rather than silent.

Ship to production

• Package models and services with Docker, expose them behind clean APIs, and deploy them to our GPU and CPU infrastructure.
• Handle the unglamorous production concerns: cold starts, timeouts, concurrency limits, versioning, rollback and monitoring.
• Own on-call-style responsibility for the AI features you build, including cost tracking.

Must-have skills

Programming & engineering

• Strong Python: type hints, async/await, dataclasses/Pydantic, clean module design, testing.
• REST API development with FastAPI (or Flask/Django with a willingness to move to FastAPI).
• Git, code review discipline, and the ability to write code someone else can maintain.
• Comfortable in Linux and on the command line.

Machine learning fundamentals

• Working knowledge of PyTorch and the Hugging Face ecosystem (transformers, tokenizers, accelerate).
• Understanding of inference-time concepts: tokenization, context windows, batching, precision (FP16/BF16/INT8), memory footprint.
• Ability to read a model card and a paper well enough to judge whether a model fits a use case.

Document processing

• Hands-on experience with at least two of: pypdfium2, PyMuPDF, pdfplumber, pdfminer.six, Docling, Unstructured, Surya, DocTR, LayoutLM family.
• Practical OCR experience (Tesseract, PaddleOCR, or a cloud OCR) and an understanding of when OCR is the wrong tool.
• Experience extracting tables from PDFs and dealing with merged cells, multi-line rows, and inconsistent column layouts.

Strongly preferred

You will be a much stronger candidate with any of these. We do not expect all of them.

Model serving & optimization

• vLLM, TGI, Ollama, llama.cpp, or Triton Inference Server.
• Quantization formats and tooling: GGUF, AWQ, GPTQ, bitsandbytes, ONNX Runtime, INT8 export.
• Serverless GPU platforms: Modal, RunPod, Replicate, Baseten including cold-start and container-lifecycle management.
• LoRA / QLoRA fine-tuning with PEFT for narrow, task-specific improvements.

Vision-language models

• Practical use of open VLMs: Qwen2.5-VL, InternVL, Granite Vision, Molmo, Phi-Vision, or similar.
• Awareness of where VLMs hallucinate especially on numeric and financial content and patterns for constraining them (using the model for layout only, sourcing values from the text layer, constrained decoding).

Orchestration & pipelines

• Workflow orchestration: Dagster, Airflow, Prefect, or Temporal.
• Async job patterns: Celery, RQ, or platform-native spawn/poll patterns.
• LLM orchestration frameworks (LangGraph, LlamaIndex, Haystack) with the judgement to know when plain Python is a better answer.
• Structured output enforcement: Instructor, Outlines, XGrammar, JSON schema / tool-use modes.

Evaluation & observability

• Building golden datasets and regression suites for extraction tasks.
• Eval tooling: promptfoo, DeepEval, Ragas, or in-house harnesses.
• LLM tracing and monitoring: Langfuse, Arize Phoenix, LangSmith, OpenTelemetry.

Nice extras

• Rule engines and policy evaluation (Open Policy Agent / Rego, Drools, rule-engine).
• Experience in fintech, lending, insurance or accounting documents.
• Handling of PII and data-security practices in document pipelines.
• Contributions to open-source ML or document-processing projects.

Why join us

• Real production ownership from month one your work goes to actual users, not a demo.
• Genuinely hard technical problems in document AI, not wrappers over an API.
• Small team, short decision cycles, direct access to leadership.
• Budget and freedom to evaluate and adopt new open-source models as they land.

To apply: send your CV along with a short note on one AI system you have taken to production what it did, what the accuracy was, and what broke.