Lead - Software Developer - Agentic AI Development OMR, Chennai, Tamil Nadu, India 5 - 8 Years Permanent
Job Description
Agentic AIDeveloper
Experience: 5+ Years | Location: Chennai, Tamil Nadu (Workfrom Office)
About the Role
We're seeking an Agentic AIDeveloper to design, build, and maintain intelligent agent-based systems thatinteract with enterprise data and workflows. You'll work with our proprietaryagentic framework, integrating enterprise systems via MCP servers and orchestratingmulti-agent workflows powered by leading LLMs - deployed securely on AWS andhybrid environments.
What You'll Do
- Design, implement, and optimize AI agent workflowswithin our in-house agentic framework
- Develop and maintain enterprise connectors through MCPservers for secure data access
- Build RAG pipelines - embeddings, vector search, andretrieval workflows for enterprise data
- Build and deploy scalable microservices and APIsconnecting AI agents with existing applications
- Manage full lifecycle: development, versioning,deployment, and maintenance via GitHub, CI/CD, containers
- Monitor model behavior, fine-tune prompts, and optimizecost-performance across LLM providers
- Collaborate cross-functionally to ensure AI agents meetoperational and compliance standards
Must-Have Skills
Programming:
- Strong software engineering fundamentals(Node.js a plus)
Agentic AI Frameworks:
- Hands-on experience with at least one: LangChain, CrewAI,LangGraph , or similar orchestration framework
- Practical experience integrating LLM APIs (ChatGPT,Claude, Gemini, Mistral, etc.) with prompt engineering best practices
AWS:
- Hands-on with AWS - Bedrock, S3, Lambda, and relatedcloud infrastructure
- Containerization experience (Docker, Kubernetes)
- Practical exposure to RAG (Retrieval-AugmentedGeneration) - vector databases, embeddings, retrieval pipelines
Observability:
- Implement monitoring, tracing, logging, andobservability for AI agents using tools such as Langfuse, OpenTelemetry ,or similar
Good to Have
- Experience with AWS Bedrock AgentCore
- Experience with Claude Agent SDK
- Evaluation : Design evaluation pipelines tomeasure agent quality, latency, hallucinations, and business outcomes
- LLMOps : Experience with prompt versioning,evaluation, observability, cost optimization, and deployment
- Frontend frameworks (React, Next.js) for agentdashboards/monitoring tools
- DevOps workflows: GitHub Actions, Terraform
- Prior experience building/maintaining multi-agentsystems at enterprise scale
- Contributions to open-source AI agentic projects orinternal AI accelerators
- Understanding of security, access management, andcompliance for enterprise AI systems
Soft Skills
- Strong analytical mindset and debugging ability
- Proven collaboration across multi-disciplinary teams(AI, infra, product)
- Curiosity-driven - stays current with fast-moving LLMand agent ecosystems
- Excellent documentation and communication skills