Sr AI Architect

Looking for an Architect with strong experience in AI and Data Engineering, preferably with hands-on experience in Generative AI (GenAI). Candidates with experience in any cloud platform (AWS, Azure, or GCP) will be considered, 

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.

Applied AI Engineer

About the Role

We are building an AI-powered platform that transforms credit origination by automating manual processes and enabling lenders to underwrite more loans with greater accuracy and lower risk.

We are looking for an experienced Applied AI Engineer to design and build production-grade Agentic AI systems capable of complex, multi-step reasoning across financial data, legal documents, and other unstructured information.

As an early engineering team member, you will take ownership of core AI architecture, multi-agent orchestration, reasoning workflows, evaluation frameworks, and scalable AI infrastructure.

Key Responsibilities

• Design and develop stateful, multi-agent AI systems for complex reasoning and decision-making.
• Build and optimize LLM pipelines using frameworks such as LangChain, DSPy, and GEPA.
• Implement RAG, prompt optimization, memory management, tool integration, and human-in-the-loop workflows.
• Develop AI evaluation frameworks using LLM-as-a-Judge and scenario-based testing.
• Implement AI observability and monitoring to track accuracy, latency, cost, and system performance.
• Build ETL pipelines and work with structured and unstructured data, SQL/NoSQL databases, vector databases, and graph-based data models.
• Integrate external tools and systems using modern agent protocols such as Model Context Protocol (MCP).
• Deploy and maintain AI services on AWS or Azure.
• Implement CI/CD pipelines, containerization, and Infrastructure as Code for reliable production deployments.

Required Qualifications

• 5+ years of professional software development experience in Python or JavaScript.
• Proven experience building and deploying production-level Agentic AI systems or complex LLM reasoning applications.
• Hands-on experience with LangChain and LLMOps, including tools such as Langfuse, Weights & Biases (W&B), or Helicone.
• Strong understanding of LLMs, RAG, prompt engineering, multi-agent orchestration, memory management, and tool calling.
• Experience with DSPy, GEPA, or advanced LLM inference and optimization techniques.
• Strong data engineering fundamentals, including ETL, SQL/NoSQL databases, and vector databases.
• Familiarity with MCP and human-in-the-loop workflows.
• Experience with AWS or Azure and modern DevOps practices, including Docker, CI/CD, and Infrastructure as Code.

Good to Have

• Experience with RLHF or RLAIF.
• Knowledge of model fine-tuning techniques such as LoRA and QLoRA.
• Experience with graph databases and graph-based data models.
• Exposure to financial services, credit underwriting, risk analysis, or document-intensive AI applications.

Why Join Us?

• Work on advanced Agentic AI and complex reasoning systems beyond conventional chatbot applications.
• Build foundational AI architecture and production-grade LLM workflows.
• Take ownership of technical decisions and system design as an early engineering team member.
• Solve challenging problems at the intersection of AI, finance, and intelligent automation.

AI Developer  

Primary Skill-set (Must have) 

• Generative AI Expertise: 2-3 years of experience in designing and implementing generative AI solutions, including knowledge of various generative and autoregressive models. Ability to apply generative AI techniques to diverse use cases such as image generation, text generation, and creative content synthesis. 

• 2 years of experience in prompt engineering, fine tuning, agentic framework, GenAI SDK’s 

• 1-2 years of experience in Agentic AI frameworks like Autogen, Lanngraph, MS Agent SDK, A2A, MCP, A2P, memory concepts, multi agent orchestration 

• 7+ years of experience in Python 

• 5+ years of experience in software development 

• Azure Proficiency: 3-5 years of experience with Azure cloud services relevant to AI, including Azure Machine Learning, Azure Cognitive Services, Azure Databricks, and Azure Kubernetes Service (AKS). 2+ years of experience in Azure's capabilities to architect end-to-end AI solutions and optimize performance. 

• Architecture Design: 3-5 years of skills with the ability to design scalable, reliable, and cost-effective architectures for AI solutions. Proficiency in designing distributed systems, microservices architectures, and containerized solutions using technologies such as Docker and Kubernetes. 

Secondary Skills (Good to have) 

• Security and Compliance: Understanding of security principles and best practices in AI development, with the ability to implement security controls, encryption mechanisms, and access management policies to protect AI models and sensitive data. 

• Integration and Deployment: Proficiency in implementing CI/CD pipelines, automation scripts, and infrastructure as code (IaC) using tools such as Azure DevOps, Terraform, or Ansible. Experience in containerization and orchestration of AI workloads using Docker and Kubernetes. 

• Software Development: Strong programming skills in languages such as Python, with experience in developing AI applications, RESTful APIs, and microservices architectures. Familiarity with software development methodologies such as Agile or Scrum. 

• Communication and Presentation: Excellent communication skills with the ability to convey complex technical concepts to non-technical stakeholders. Experience in preparing and delivering technical presentations, architecture diagrams, and documentation to communicate architectural decisions and design rationale effectively. 

Strong Lead AI Engineer Profile with agentic systems architecture expertise

2

Mandatory (Experience 1): Must have 6+ years of software or ML engineering, with at least recent 2+ years building and shipping production LLM or agentic AI systems

3

Mandatory (Tech skill 1): Must have hands-on proficiency with at least two agentic frameworks (LangGraph, LangChain, AutoGen, CrewAI), with experience debugging framework internals

4

Mandatory (Tech skill 2): Must have direct SDK experience with Anthropic Claude API (tool use, streaming), OpenAI Assistants API, or Vertex AI Agent Builder

5

Mandatory (Tech skill 3): Must have Python mastery — production-quality code, type annotations, unit and integration tests, packaging, and performance profiling

6

Mandatory (Tech skill 4): Must have RAG pipeline depth — embedding model selection, vector stores (Pinecone, Weaviate, pgvector), hybrid retrieval, RAGAS or custom evaluation harnesses

7

Mandatory (Tech skill 5): Must have cloud deployment experience with AWS, Azure, or GCP; Docker, Kubernetes, IaC basics (Terraform or CDK), and CI/CD pipelines

8

Mandatory (Tech skill 6): Must have agent observability experience — LangSmith, Helicone, or equivalent — with ability to diagnose latency, cost, and quality issues in production traces

9

Mandatory (Tech skill 8) : Must have owned full sub-system designs — agent topology, data flows, API contracts, failure handling — for a bounded scope, and built multi-agent graphs, tool orchestration, retrieval, and memory systems.

10

Mandatory (Tech skill 7): Must have track record of shipping 2+ agentic or ML systems to production — not just proof-of-concepts — with documented performance benchmarks

11

Mandatory (Communication): Must be able to write crisp component specifications and communicate architectural trade-offs to both engineers and non-technical stakeholders

Strong Lead AI Engineer Profile with agentic systems architecture expertise

2

Mandatory (Experience 1): Must have 6+ years of software or ML engineering, with at least recent 2+ years building and shipping production LLM or agentic AI systems

3

Mandatory (Tech skill 1): Must have hands-on proficiency with at least two agentic frameworks (LangGraph, LangChain, AutoGen, CrewAI), with experience debugging framework internals

4

Mandatory (Tech skill 2): Must have direct SDK experience with Anthropic Claude API (tool use, streaming), OpenAI Assistants API, or Vertex AI Agent Builder

5

Mandatory (Tech skill 3): Must have Python mastery — production-quality code, type annotations, unit and integration tests, packaging, and performance profiling

6

Mandatory (Tech skill 4): Must have RAG pipeline depth — embedding model selection, vector stores (Pinecone, Weaviate, pgvector), hybrid retrieval, RAGAS or custom evaluation harnesses

7

Mandatory (Tech skill 5): Must have cloud deployment experience with AWS, Azure, or GCP; Docker, Kubernetes, IaC basics (Terraform or CDK), and CI/CD pipelines

8

Mandatory (Tech skill 6): Must have agent observability experience — LangSmith, Helicone, or equivalent — with ability to diagnose latency, cost, and quality issues in production traces

9

Mandatory (Tech skill 8) : Must have owned full sub-system designs — agent topology, data flows, API contracts, failure handling — for a bounded scope, and built multi-agent graphs, tool orchestration, retrieval, and memory systems.

10

Mandatory (Tech skill 7): Must have track record of shipping 2+ agentic or ML systems to production — not just proof-of-concepts — with documented performance benchmarks

11

Mandatory (Communication): Must be able to write crisp component specifications and communicate architectural trade-offs to both engineers and non-technical stakeholders

12

Mandatory (Note 1) : Role is Hybrid, WFH flexibility as well upto 6 days a month

Job Details

Position Title: AI Evangelist

Role Purpose

We are seeking a highly experienced AI Evangelist & Core AI Engineer who combines deep technical expertise in Artificial Intelligence with the ability to influence, educate, demonstrate, and accelerate AI adoption across the enterprise.

The role requires deep understanding of AI, Machine Learning, Deep Learning, Generative AI, Large Language Models, Agentic AI, AI engineering, and modern software development practices, combined with significant hands-on experience implementing scalable AI applications in complex enterprise environments.

Key Responsibilities

1. Core AI Engineering & Architecture

• Design, develop, and implement enterprise-grade AI and Generative AI applications.
• Build scalable applications using LLMs, multimodal models, AI agents, RAG, vector databases, knowledge graphs, APIs, and enterprise data platforms.
• Architect AI solutions capable of supporting enterprise-scale workloads with appropriate considerations for:
• Scalability
• Reliability
• Security
• Performance
• Observability
• Cost optimization
• Governance
• Develop and implement advanced Retrieval-Augmented Generation (RAG) architectures including hybrid search, reranking, metadata filtering, semantic retrieval, and knowledge grounding.
• Build multi-agent and agentic AI applications capable of reasoning, tool usage, workflow execution, orchestration, and enterprise system integration.
• Design AI applications integrating structured and unstructured enterprise information.
• Evaluate architecture choices between commercial models, open-source models, small language models, domain-specific models, and hosted AI platforms.
• Implement model routing, prompt orchestration, caching, guardrails, evaluation pipelines, and fallback strategies.
• Work closely with cloud, platform, security, enterprise architecture, DevOps, and application engineering teams.

2. Deep AI / ML / DL Expertise

The candidate should have strong conceptual and practical understanding across the modern AI technology landscape, including:

• Artificial Intelligence /Machine Learning/ Deep Learning/ Neural Networks /LLM/SLM/RAG/Graph RAG / MLOps / LLMOps / GenAIOps

3. Generative AI & LLM Engineering

• Build production-grade applications utilizing leading commercial and open-source LLM ecosystems.
• Design scalable LLM platforms supporting multiple enterprise applications and use cases.
• Develop reusable LLM services, APIs, components, agent frameworks, and reference architectures.

4. AI Agents & Automation

• Design and implement AI agents and agentic workflows that automate complex business and engineering processes.
• Build agents capable of interacting with enterprise applications, APIs, databases, documents, development environments, and workflow platforms.
• Evaluate emerging agent architectures and orchestration frameworks pragmatically.
• Develop reusable patterns for:
• Single-agent systems
• Multi-agent systems
• Human-in-the-loop workflows
• Autonomous workflows
• Tool-calling agents
• Coding agents
• Enterprise knowledge agents
• Establish appropriate controls for AI agent identity, permissions, auditability, security, and human oversight.

5. AI-Enabled Software Engineering

Drive adoption of AI throughout the Software Development Life Cycle.

Title - AI Architect

Experience: 8–12 years

Location: Hyderabad (Hybrid)

Role Summary:

We P99Soft are looking for a senior AI Architect to own system-level design and architecture decisions across a portfolio of production AI initiatives. This role goes beyond assembling common frameworks - it requires the judgment to evaluate deep architectural trade-offs (model quality vs. size vs. cost, deterministic vs. generative approaches, and verification/testing strategy) and translate them into coherent, maintainable system architecture at scale.

Key Responsibilities:

• Define end-to-end system architecture and technical direction for AI-driven platforms, spanning retrieval-augmented generation, agentic/tool-using systems, vision and language model applications, and semantic search.
• Evaluate and own core architectural trade-offs: model quality vs. size vs. cost, deterministic vs. generative system design, latency and scalability, and the design of output-verification and evaluation harnesses.
• Provide technical leadership and design review across multiple concurrent initiatives, guiding implementation teams on build-out.
• Track and apply emerging AI/ML research and techniques where they meaningfully improve system design and reliability.
• Define the boundary between deterministic, verifiable system components and generative/agentic components based on the problem being solved.
• Serve as the technical escalation point for complex system-level issues — reliability, performance, or output-quality problems beyond routine debugging.

Required Experience & Skills:

• 8–12 years of overall engineering experience, including substantial hands-on depth in applied or foundational AI/ML system design - this is a non-negotiable baseline, not familiarity with AI tools as an end user.
• Demonstrated experience architecting AI/ML systems at production scale, beyond simple retrieval or prompt-based implementations.
• Strong grasp of trade-offs across model quality, size, cost, latency, and determinism, and how these decisions shape system architecture.
• Working knowledge of current and emerging generative AI / LLM techniques and research directions, and the ability to evaluate when they are appropriate to apply.
• Experience architecting one or more of: retrieval-augmented generation pipelines, agentic/tool-using systems, vision models, semantic search, or automated verification and evaluation systems.
• Comfort operating across multiple concurrent initiatives and translating research-adjacent concepts into buildable, production-grade systems.

Nice to Have:

• Experience in domains with strong internal-tooling or quality/verification requirements.
• Exposure to developer-facing tooling or code-analysis systems.

Benefits

• Competitive salary and performance-based bonuses.
• Comprehensive health insurance.
• Paid time off and flexible working hours.
• Professional development opportunities and support for continuing education.
• Udemy Learning Licenses to enhance skills and stay up-to-date with the latest technology.

P99Soft is an Equal-Opportunity Employer

P99Soft is an equal-opportunity employer. At P99soft, we are committed to providing equal employment opportunities regardless of job history, disability, gender identity, religion, race, color, caste, marital/parental status, veteran status, or any other special status. We stand against the discrimination of employees and individuals and are proud to be an equitable workplace that welcomes individuals from all walks of life if they fit the designated roles and responsibilities.

Life @ P99Soft

At P99soft, we believe in creating a work environment that balances professional excellence with personal well-being. Our vibrant office culture is built on mutual respect, inclusivity, and a shared passion for innovation. We host regular team-building activities, workshops, and social events to foster a sense of community and collaboration among our employees. Join us and be part of a team that values your contributions and supports your growth.

About Us

P99soft is a leading IT Services and IT Consulting company dedicated to making our customers' business operations seamless by providing them with digital services and applications using the latest technologies. We are committed to bringing excellence to all our creations. We need passion, empathy, and being customer-focused to achieve technical excellence. We believe in transparency through open communication and work with honesty and integrity while dealing with our customers and partners.

Our Vision: “To lead digital transformation for our customers, delighting them at every step, while empowering our employees and fostering success.”

Our Mission: “To attain our objectives within a framework of integrity, transparency, and respect for our clients, employees, partners, and the community, fostering mutual trust and sustainable growth.”

Journey towards digital transformations begins here. Our talented teams help you make informed decisions, enhance operation efficiencies, create state-of-the-art visual interfaces, and design dynamic workflows to bring a better customer experience. Our engineering teams take complete ownership of assigning the right talent and architecting solutions using the latest technologies.

Support with design and build to prove out agentic AI solution flow by working with other data 

scientists and engineers to build, train Large Language Model (LLM) architectures, RAG 

systems, and autonomous agentic workflows 

Key qualifications: 

>> AI solution design & Development: Design Agentic AI solutions using RAG (Retrieval-

Augmented Generation) and orchestration frameworks like LangGraph or LangChain. 

>> Model Fine-Tuning: Solid understanding and experience with Pre-train, fine-tune, and 

optimize open-source like BERT, LLama, and other proprietary foundation models for domain-

specific tasks 

>> Solid Stats and ML foundations and (vibe) coding skills with Python, PySpark 

>>  Implement validation frameworks and tracing practices (using tools like Arize) to monitor 

agent behavior, guard against model drift, and ensure compliance 

>> Collaborate with Engineering to deploy models securely on cloud and on-prem ecosystems 

Design and develop Agentic AI systems using LLMs, tools, memory,

workflows, and MCP.

Build production-grade RAG pipelines, including ingestion, chunking,

embeddings, retrieval, reranking, and evaluation.

Implement context engineering strategies for improving LLM accuracy,

relevance, and reliability.

Develop and integrate MCP-based tools and services for AI agents.

Work with LLMs, SLMs, quantized models, and model optimization

techniques for efficient inference.

Develop scalable backend services and APIs for AI applications.

Design databases and data models supporting AI/agentic applications.

Implement AI observability covering latency, token usage, cost, failures,

quality, and agent/tool execution.

Apply AI governance and responsible AI practices, including security,

access control, data privacy, and auditability.

Optimize AI systems for latency, scalability, cost, and reliability.

Collaborate with engineering and product teams to take AI solutions from

POC to production.

Strong hands-on experience with GenAI, LLMs, and Agentic AI.

Experience building RAG applications.

Strong understanding of Context Engineering and prompt/context

optimization.

Role Overview

We are looking for a hands-on AI/ML Engineer to design, develop, and deploy

production-ready GenAI and Agentic AI applications. The role involves building

intelligent agents, RAG pipelines, AI APIs, backend services, and scalable AI

infrastructure with a strong focus on context engineering, observability,

governance, and model optimisation.

Key Responsibilities

Required Skills

Practical experience with MCP (Model Context Protocol).

Experience with frameworks such as LangChain, LangGraph,

LlamaIndex, or equivalent.

Knowledge of LLM/SLM deployment and quantization techniques.

Strong Python backend development experience.

Experience developing REST APIs using FastAPI/Flask or equivalent.

Strong understanding of SQL/NoSQL databases and database design.

Experience with vector databases such as Qdrant, Pinecone, Weaviate,

ChromaDB, or FAISS.

Understanding of AI observability, evaluation, monitoring, and

governance.

Experience with cloud platforms and production deployment is preferred.

Strong understanding of software engineering principles, Git, testing, and

CI/CD.