Experience: 5 - 10 years

Location: Hyderabad/Mumbai/Bangalore/Indore/Chennai/Gift :
Solid hands-on experience building AI/LLM-powered systems end-to-end.
Expertise with LangChain and LangGraph.
Deep proficiency in Python for Al pipelines, APIs, and orchestration.
Solid understanding of embeddings, chunking, retrieval architectures, and ranking strategies.
Experience with open-source LLMs (Llama, Mistral, Falcon, Mixtral, etc.)
Experience deploying full-stack enterprise applications.
Experience with vector database design and optimization.
Robust knowledge of Kubernetes, Docker, CI/CD, microservices, and cloud deployment patterns.
Bands-on experience integrating solutions with Microsoft Copilot.
Experience with Al evaluation, observability, and model governance Key responsibilities:
Design and implement full end to end RAG pipelines (ingestion, chunking, embeddings, retrieval, ranking)
Build scalable Al workflows using LangChain, LangGraph, and agent-based architectures.
Develop backend services and APIs in Python, ensuring scalability,



security, and maintainability.
Create full-stack UIs for GenAl applications (React, Angular, Vue, etc.)
Integrate and optimize vector databases (Pinecone, ChromaDB, Weaviate, Milvus)
Implement Microsoft Copilot integrations across enterprise workflows and apps.
Build evaluation frameworks, observability pipelines, and quality guardrails using tools such as RAGAS, LangSmith, or custom evaluation metrics.
Implement enterprise authentication and access (OAuth, Azure AD, Okta)
Optimize model performance, inference latency, indexing strategies, and retrieval accuracy.
Ensure proper DevOps (Docker, Kubernetes), CI/CD, and release management for all Al components.
Collaborate with cross-functional teams to drive Al adoption and ensure scalable, maintainable solutions.
Provide long-term support, model updates, error handling, and operational governance

📌 Generative Ai Engineer Bengaluru
🏢 Tata Consultancy Services
📍 Bengaluru