Staff Software Engineer, AI Agents

Software Engineer

Position Responsibilities

You will primarily execute within defined frameworks and grow your independent scope over time. The following reflects what you will own and contribute to:

Build & Integrate

• Build and maintain AI-enabled workflows, platform integrations, and internal tools using PHP, JavaScript, Workato, and Web Services
• Develop prototypes and proofs of concept; contribute to production deployments under senior guidance
• Implement and test integrations between Deltek's support platforms and internal data systems.

Analyse & Solve

• Break down defined problems into actionable tasks; identify risks, dependencies, and edge cases before they surface in production
• Troubleshoot complex issues across the full stack and document root cause findings clearly
• Investigate stakeholder-reported issues to identify whether the problem is technical, process-related, or both.

Operate & Improve

• Follow established governance, architecture, and deployment processes; raise improvement suggestions through proper channels
• Write and maintain documentation for systems, workflows, business rules, and solution designs
• Participate actively in sprint ceremonies; manage your own tasks and flag blockers early
• Demonstrate continuous learning in AI, automation, and integration technologies — this space moves fast and curiosity is part of the job.

Nice-to-Have Skills

The following are not required for the role, but candidates with depth in any of these areas will stand out. Listed in rough order of relevance to this team's current work:

Oracle Service Cloud

Workato / iPaaS

Salesforce

Gainsight

AI / LLM integration

Snowflake

Microsoft Power BI

Microsoft Power Apps

Cloud-native development

Experience with AI tools (GitHub Copilot, LLM APIs, automation agents) used in an operational or product context — not just personal experimentation — is a genuine plus for this team.

Qualifications

• Education: Bachelor's degree in Computer Science, Information Technology, Engineering, or a related technical discipline. Equivalent practical experience considered.
• Experience: 2–4 years of hands-on experience in software engineering, systems integration, or a closely related field. Internship and co-op experience counts if it involved real production systems.
• Coding: Demonstrable PHP and/or JavaScript experience — a portfolio, GitHub profile, or code sample you can speak to will strengthen your application.
• Collaboration model: Comfortable working remotely with distributed teams. The role requires regular overlap with US East/Central time zones (approximately 2:00 PM – 11:00 PM IST for at least part of the week).
• Language: Strong written and spoken English is essential — much of the collaboration with stakeholders and senior engineers happens asynchronously in writing.

Senior AI Engineer

Code Generation, Agent Architecture & LLM Systems

📍 Mumbai (On-site) | Full-time | 5+ years

About the Role:

Unico Connect is an AI-first technology partner that builds custom mobile, web, and AI products for clients across multiple geographies.

We are hiring a Senior AI Engineer for a dedicated client engagement focused on building an AI-powered application builder platform - a product where users describe software in plain English and the system generates, previews, and iteratively refines working code.

The mandatory requirement for this role is hands-on production experience shipping LLM-powered systems with agent architectures, with experience in code generation or developer tooling contexts a strong advantage.

The role is product-focused and deeply hands-on. You will own everything between the user's prompt and correct code landing in the project: the agentic loop, code generation pipeline, context management, evaluation suite, and model cost strategy.

You will work alongside the Senior MLOps Engineer who operationalises the infrastructure around your system, and collaborate closely with backend, frontend, and DevOps engineers.

Responsibilities:

Agent Architecture

Design and own the agentic loop for the platform - request interpretation, planning, tool-calling sequence (read file, edit file, run build, search code, install package), and stop conditions.

Make and revisit architectural decisions on single-agent vs. multi-agent designs, including planner/executor splits and dedicated build-repair sub-agents.

Code Generation Pipeline

Own the end-to-end generation flow: task classification, context gathering, planning, targeted edits, verification, and commit.

Implement diff/search-replace-based file editing with fuzzy matching and fallback strategies.

Enforce scope discipline so the agent makes minimal diffs and does not modify code it was not asked to touch.

Self-Repair Loop

Build and tune the automated repair loop that pipes compiler, lint, build, and runtime errors back to the model with retry budgets and model escalation.

This loop is the primary quality lever - the difference between 60-70% and 90%+ build success rates.

Context Management

Build file-relevance retrieval so the agent sees the right files, not the whole codebase: dependency graphs, AST/tree-sitter-based chunking, embeddings, recency signals, and hybrid retrieval.

Implement conversation summarisation and memory for long sessions, and address long-project degradation through codebase summaries and periodic consistency passes.

Own token budgeting and prompt caching strategy.

Prompt Engineering as a Discipline

Own the system prompt and per-task prompt variants (new feature, bug fix, styling change).

Maintain few-shot examples and enforce coding conventions, stack rules, and prohibited behaviours such as no hardcoded secrets and no whole-file rewrites.

Version prompts like code with changelogs and rollback capability.

Evaluation and Quality Measurement

Design and own the evaluation suite: representative test prompts run on every prompt and model change, scored on build success rate, instruction adherence, and output quality including LLM-as-judge and visual/screenshot checks where relevant.

Define regression gates that block quality-degrading changes from shipping.

Treat evals the way engineers treat automated testing: versioned, automated, and tracked over time.

This responsibility is non-negotiable at this level.

Model Strategy and Cost

Design model routing - cheap and fast models for classification and small edits, frontier models for complex generation.

Drive cost optimisation through prompt caching, diff-based edits over full-file rewrites, and tighter context selection.

Track cost per agent run and tokens per task; evaluate new model releases against the eval suite and lead migrations when results justify it.

Safety and Reliability of Agent Behaviour

Defend against prompt injection from user content and fetched web content.

Ensure secrets never appear in generated client code.

Define what the agent's tools may and may not do in collaboration with the platform team.

Contribute to output moderation and abuse-pattern awareness.

Mentorship and Engineering Standards

Run code reviews, define engineering conventions for AI work, and raise the engineering bar across the AI team.

Work closely with the Senior MLOps Engineer on handoff of eval design, prompt configurations, and model routing logic.

Requirements:

Hands-on Production Ownership of LLM-Powered Systems with Agent Architectures (Mandatory)

Must have personally shipped and operated at least one complex production AI system - agentic, multi-step, or code generation - with end-to-end ownership of architecture, evaluation, and cost.

POCs, internal demos, and tutorial-grade work do not qualify.

5+ Years of Professional Software or AI Engineering Experience

With at least 3 years focused on LLM applications, AI engineering, or production AI systems.

Candidates with strong backend backgrounds and a clear, substantive pivot into LLM systems qualify.

Strong Python Proficiency and Service Development

Production-grade Python with FastAPI or equivalent: type hints, async patterns, streaming responses, testing, and packaging.

Not notebook-only.

Depth Across LLM APIs and Agent Systems

Production experience with at least two of OpenAI, Anthropic Claude, Google Gemini, or open-weight models (vLLM, Ollama, Together).

Production experience with at least one agent framework (LangGraph, CrewAI, AutoGen, LlamaIndex Agents) or hand-rolled equivalent.

Hands-on with tool calling, structured outputs, and multi-step reasoning.

Demonstrated, Systematic Evaluation Practice - Non-Negotiable

Must have built evaluation harnesses that gate production releases, not ad-hoc testing.

Hands-on with at least one of LangSmith, Langfuse, Promptfoo, Ragas, or DeepEval.

Candidates with no systematic answer to evaluation should not be considered at senior level regardless of other strengths.

Cost Discipline for Production AI

Track record of measurable cost optimisation on production AI features.

Able to speak in specifics: cost per request, savings achieved through caching or model routing, context reduction decisions.

AWS Working Knowledge

Hands-on with EC2, S3, IAM, and Docker.

Comfort with CI/CD workflows and deploying AI services.

Awareness of LLM Security Failure Modes

Familiar with prompt injection patterns, understands that system prompt rules alone are insufficient, and has experience with output validation and content safety in production.

Nice to Have

• Experience with AST/tree-sitter tooling, diff-based editing systems, or compiler-adjacent work
• MCP server authoring
• Open-source AI contributions
• Published technical writing on LLM systems
• Multi-modal model experience
• Fine-tuning exposure (LoRA, QLoRA, PEFT)

Role

We are looking for a Full Stack Engineer who can own the entire technical stack, design systems that scale, and ship products fast. You will work across frontend, backend, and AI systems, making key architectural decisions while building a product used by real users.

This role offers high ownership, where engineers move ideas to production quickly and take responsibility for both technical decisions and product impact.

What would you do?

• Build and own the end-to-end platform using React, Node.js microservices, Python AI agents, and AWS.
• Design and implement scalable system architecture, including caching, databases, and state management between AI and UI.
• Develop AI-powered backend services and orchestrate LLM workflows using modern frameworks.
• Build highly interactive front-end experiences using modern React and real-time communication tools.
• Define and maintain engineering best practices, including CI/CD pipelines, monorepo structures, and development workflows.
• Collaborate closely with users and product teams to identify problems and ship impactful solutions.
• Continuously simplify systems by removing unnecessary complexity and keeping architecture clean.

Who should apply?

• Engineers with 4+ years of experience building and shipping production-grade products.
• Strong understanding of system design, architecture, and scalable backend systems.
• Hands-on experience with Python (FastAPI, async systems) and LLM-based applications.
• Proficiency in JavaScript / TypeScript with Node.js and modern backend frameworks.
• Experience building modern frontend applications using React (React 18+).
• Familiarity with databases such as Redis, PostgreSQL, or MongoDB, and designing scalable APIs.
• Engineers comfortable working in fast-paced environments with high ownership and minimal process overhead.

Technical Skills

• Backend: Node.js, Express, Python, FastAPI
• Frontend: React (React 18+), interactive UI development
• AI/LLM Systems: LLM orchestration, multi-model integrations
• Databases: Redis, PostgreSQL, MongoDB
• Infrastructure: AWS, CI/CD pipelines, microservices architecture
• Real-time Systems: Socket.IO, Server-Sent Events (SSE)

Job Title : Python Backend Engineer (with MLOps & LLMOps Experience)

Experience : 4 to 8 Years

Location : Gurgaon Sector - 43

Employment Type : Full-time

Job Summary :

We are looking for an experienced Python Backend Engineer with a strong background in FastAPI, Django, and hands-on exposure to MLOps and LLMOps practices.

The ideal candidate will be responsible for building scalable backend solutions, integrating AI/ML models into production environments, and implementing efficient pipelines for machine learning and large language model operations.

Mandatory Skills : Python, FastAPI, Django, MLOps, LLMOps, REST API development, Docker, Kubernetes, Cloud (AWS/Azure/GCP), CI/CD.

Key Responsibilities :

• Develop, optimize, and maintain backend services using Python (FastAPI, Django).
• Design and implement API endpoints for high-performance and secure data exchange.
• Collaborate with data science teams to deploy ML/LLM models into production using MLOps/LLMOps best practices.
• Build and manage CI/CD pipelines for ML models and ensure seamless integration with backend systems.
• Implement model monitoring, versioning, and retraining workflows for machine learning and large language models.
• Optimize backend performance for scalability and reliability in AI-driven applications.
• Work with Docker, Kubernetes, and cloud platforms (AWS/Azure/GCP) for deployment and orchestration.
• Ensure best practices in code quality, testing, and security for all backend and model deployment workflows.

Required Skills & Qualifications :

• 4 to 8 years of experience as a Backend Engineer with strong expertise in Python.
• Proficient in FastAPI and Django frameworks for API and backend development.
• Hands-on experience with MLOps and LLMOps workflows (model deployment, monitoring, scaling).
• Familiarity with machine learning model lifecycle and integration into production systems.
• Strong knowledge of RESTful APIs, microservices architecture, and asynchronous programming.
• Experience with Docker, Kubernetes, and cloud environments (AWS, Azure, or GCP).
• Exposure to CI/CD pipelines and DevOps tools.
• Good understanding of Git, version control, and testing frameworks.

Nice to Have :

• Experience with LangChain, Hugging Face, or similar LLM frameworks.
• Knowledge of data pipelines, feature engineering, and ML frameworks (TensorFlow, PyTorch, etc.).
• Understanding of vector databases (Pinecone, Chroma, etc.).

Education :

• Bachelor’s or Master’s degree in Computer Science, Engineering, or related field.

About Techjays

At Techjays, we build production-grade AI platforms for global clients. We operate at the intersection of backend engineering, distributed systems, and applied AI — delivering secure, scalable, and enterprise-ready intelligent systems. Our team has built and scaled products at Google, Akamai, NetApp, ADP, Cognizant, and Capgemini.

About the Role

This is not a feature-delivery role. We are looking for an AI Lead who can architect, own, and scale intelligent backend systems end-to-end. You will drive both technical direction and execution — working across LLM integrations, RAG pipelines, agentic AI workflows, and cloud-native backend systems for global clients.

What You'll Do

• Architect and scale backend systems powering AI-driven applications
• Design and implement RAG pipelines, AI agents, and LLM integrations
• Own systems end-to-end — from architecture to deployment and scaling
• Integrate and optimize LLMs (Claude, GPT, Gemini) for real-world production use cases
• Build high-performance distributed systems with observability and cost efficiency
• Lead backend and AI initiatives with strong technical ownership
• Mentor engineers and raise the technical bar across teams
• Collaborate with product and AI teams to deliver AI-native solutions

What We're Looking For

• 6–10 years of strong backend engineering experience
• Hands-on expertise in Python (FastAPI / Django / Flask)
• Deep understanding of Generative AI and LLM-based systems
• Strong experience with RAG pipelines and Vector Databases (Pinecone, FAISS, ChromaDB, Weaviate)
• Solid knowledge of Agentic AI — building autonomous agents and multi-agent workflows
• Proficiency in AWS or GCP in production environments
• Experience with distributed systems, microservices, and system design
• Strong grasp of Data Structures, Algorithms, and Design Patterns
• Familiarity with WebSockets, Git, Linux/Unix, and CI/CD

Nice to Have

• Experience with Anthropic Claude API and Claude Code
• Familiarity with real-time data systems or streaming (Kafka, etc.)
• MLOps and AI system lifecycle experience
• Optimizing AI systems for latency, cost, and scalability

Who You Are

• You think in systems, not just features
• You take full ownership of what you build
• You are comfortable navigating fast-moving, ambiguous environments
• You stay updated with the latest in Generative AI and backend technologies
• Strong communicator who can collaborate across teams and global clients

What We Offer

• Competitive compensation (Best in Industry)
• Work on production-grade AI systems used by global clients
• Exposure to cutting-edge AI tools and frameworks
• A culture that values clarity, integrity, and continuous growth

About the Role

At Techjays, we build production-grade AI systems for global clients. We are looking for a Solution Architect who can bridge the gap between client needs and technical delivery — someone who can walk into a client room, understand their business challenges, and walk out with a compelling, technically sound AI solution.

This role sits at the intersection of pre-sales, solutioning, and delivery governance.

What You'll Do

• Own end-to-end solutioning from client discovery to architecture design
• Partner with pre-sales teams on RFPs, proposals, and client presentations
• Define architectures for LLM integrations, RAG pipelines, and agentic workflows
• Conduct architecture reviews and technical assessments for ongoing projects
• Act as a trusted technical advisor to enterprise clients during pre-sales

Key Skills

• Python, REST APIs, Microservices, Distributed Systems
• AWS / Azure / GCP, Docker, Kubernetes, CI/CD
• LLM Integrations, RAG Pipelines, AI Agents, Vector Databases
• Enterprise data architecture and integration patterns
• Strong client communication and presentation skills

Who You Are

• Client-first mindset — listens, understands, and translates business pain into technical clarity
• Strong communicator comfortable with C-level stakeholders
• High ownership — accountable for every solution you sign off on
• Collaborative across sales, delivery, and engineering

What We Offer

• Flexible work environment
• Paid holidays & flexible time off
• Medical insurance (Self & Family up to ₹4 Lakhs)
• Exposure to global clients and high-impact pre-sales engagements
• A culture of clarity, integrity, and continuous growth

Who we are: My AI Client is building the foundational platform for the "agentic economy," moving beyond simple chatbots to create an ecosystem for autonomous AI agents and they aim to provide tools for developers to launch, manage, and monetize AI agents as "digital coworkers."

The Challenge

The current AI stack is fragmented, leading to issues with multimodal data, silent webhook failures, unpredictable token usage, and nascent agent-to-agent collaboration. My AI Client is building a unified, robust backend to resolve these issues for the developer community.

Your Mission

As a foundational member of the backend team, you will architect core systems, focusing on:

• Agent Nervous System: Designing agent-to-agent messaging, lifecycle management, and high-concurrency, low-latency communication.
• Multimodal Chaos Taming: Engineering systems to process and understand real-time images, audio, video, and text.
• Bulletproof Systems: Developing secure, observable webhook systems with robust billing, metering, and real-time payment pipelines.

What You'll Bring

• My AI Client seeks an experienced engineer comfortable with complex systems and ambiguity.

Core Experience:

● Typically 3 to 5 years of experience in backend engineering roles.

● Expertise in Python, especially with async frameworks like FastAPI.

● Strong command of Docker and cloud deployment (AWS, Cloud Run, or similar).

● Proven experience designing and building microservice or agent-based architectures.

Specialized Experience (Ideal):

• Real-Time Systems: Experience with real-time media transmission like WebRTC, WebSockets and ways to process them.
• Scalable Systems: Experience in building scalable, fault-tolerant systems with a strong understanding of observability, monitoring, and alerting best practices.
• Reliable Webhooks: Knowledge of scalable webhook infrastructure with retry logic, backoffs, and security.
• Data Processing: Experience with multimodal data (e.g., OCR, audio transcription, video chunking with FFmpeg/OpenCV).
• Payments & Metering: Familiarity with usage-based billing systems or token-based ledgers.

Your Impact

• The systems designed by this role will form the foundation for:
• Thousands of AI agents for major partners across chat, video, and APIs.
• A new creator economy enabling developers to earn revenue through agents.
• The overall speed, security, and scalability of my client’s AI platform.

Why Join Us?

• Opportunity to solve hard problems with clean, scalable code.
• Small, fast-paced team with high ownership and zero micromanagement.
• Belief in platform engineering as a craft and care for developer experience.
• Conviction that AI agents are the future, and a desire to build their powering platform.
• Dynamic, collaborative in-office work environment in Bengaluru in a Hybrid setup (weekly 2 days from office)
• Meaningful equity in a growing, well-backed company.
• Direct work with founders and engineers from top AI companies.
• A real voice in architectural and product decisions.
• Opportunity to solve cutting-edge problems with no legacy code.

Ready to Build the Future?

My AI Client is building the core platform for the next software paradigm. Interested candidates are encouraged to apply with their GitHub, resume, or anything that showcases their thinking.

Job Title: Backend Engineer – Python (AI Backend)

Location: Bangalore, India

Experience: 1–2 Years

Job Description

We are looking for a Backend Engineer with strong Python skills and hands-on exposure to AI-based applications. The candidate will be responsible for developing scalable backend services and supporting AI-powered systems such as LLM integrations, AI agents, and RAG pipelines.

Key Responsibilities

• Develop and maintain backend services using Python (FastAPI preferred)
• Build and manage RESTful APIs for frontend and AI integrations
• Support development of AI-driven features (LLMs, RAG systems, AI agents)
• Design and maintain both monolithic and microservices architectures
• Optimize database performance and backend scalability
• Work with DevOps for Docker-based deployments

Required Skills

• Strong experience in Python backend development
• Hands-on experience with FastAPI / Django / Flask
• Knowledge of REST APIs and microservices
• Experience with AI applications (LLM usage, prompt engineering basics)
• Database knowledge: MongoDB, PostgreSQL or MySQL
• Experience with Docker and basic cloud platforms (AWS/GCP/Azure)
• Hands-on experience with Redis for caching and in-memory storage

Good to Have

• Experience integrating payment gateways (Razorpay, Stripe, PayU, etc.)
• Exposure to event-driven architectures using RabbitMQ, Kafka, or Redis Streams
• Kubernetes
• Understanding of model fine-tuning concepts

About Wokelo:

Wokelo is an LLM agentic platform for investment research and decision making. We automate complex research and analysis tasks traditionally performed by humans. Our platform is leveraged by leading Private Equity firms, Investment Banks, Corporate Strategy teams, Venture Capitalists, and Fortune 500 companies.

With our proprietary agentic technology and state-of-the-art large language models (LLMs), we deliver rich insights and high-fidelity analysis in minutes—transforming how financial decisions are made.

Headquartered in Seattle, we are a global team backed by renowned venture funds and industry leaders. As we rapidly expand across multiple segments, we are looking for passionate individuals to join us on this journey.

Requirements:

• 0-1 years of experience as a Software Developer.
• Bachelor’s or Master’s degree in Computer Science or related field.
• Proficiency in Python with strong experience in Django Rest Framework.
• Hands-on experience with Django ORM.
• Ability to learn quickly and adapt to new technologies.
• Strong problem-solving and analytical skills.
• Knowledge of NLP, ML models, and related engineering practices (preferred).
• Familiarity with LLMs, RLHF, transformers, embeddings (a plus).
• Prior experience in building or scaling a SaaS platform (a plus).
• Strong attention to detail with experience integrating testing into development workflows.

Key Responsibilities:

• Develop, test, and maintain scalable backend services and APIs using Python (Django Rest Framework).
• Work with Django ORM to build efficient database-driven applications.
• Collaborate with cross-functional teams to design and implement features that enhance the Wokelo platform.
• Contribute to NLP engineering and ML model development to power GenAI solutions (preferred but not mandatory).
• Ensure testing and code quality are embedded into the development process.
• Research and adopt emerging technologies, providing innovative solutions to complex problems.
• Support the transition of prototypes into production-ready features on our SaaS platform.
• Perform adhoc tasks as and when required/assigned by manager.

Why Join Us?

• Opportunity to work on a first-of-its-kind Generative AI SaaS platform.
• A steep learning curve in a fast-paced, high-growth startup environment.
• Exposure to cutting-edge technologies in NLP, ML models, LLM Ops, and DevOps.
• Collaborative culture with global talent and visionary leadership.
• Full health coverage, flexible time-off, and remote work culture.

As a Python Engineer, you will play a critical role in building and scaling data pipelines, developing prompts for large language models (LLMs), and deploying them as efficient, scalable APIs. You will collaborate closely with data scientists, product managers, and other engineers to ensure seamless integration of data solutions and LLM functionalities. This role requires expertise in Python, API design, data engineering tools, and a strong understanding of LLMs and their applications.