Key Responsibilities

• Design and build enterprise-grade Generative AI applications
• Develop RAG pipelines and LLM-based solutions
• Build agentic workflows using LangChain and/or LangGraph
• Implement embeddings, chunking, semantic search, and retrieval optimization
• Work with vector databases such as ChromaDB, Qdrant, Pinecone, FAISS, or Azure AI Search
• Develop and expose REST APIs using FastAPI/Flask
• Deploy and manage applications using Docker, Kubernetes, and cloud platforms (Azure/AWS)
• Apply prompt engineering techniques to optimize LLM performance
• Support CI/CD pipelines for production GenAI deployments

Requirements

• 4-6 years of overall experience
• Strong Python programming skills
• Hands-on experience with RAG and LLM-based applications
• Experience with LangChain and/or LangGraph
• Experience with vector databases (ChromaDB, Qdrant, Pinecone, FAISS, Azure AI Search, etc.)
• Strong understanding of prompt engineering and agentic AI workflows
• Experience with embeddings, chunking, semantic search, and retrieval optimization
• Experience with FastAPI/Flask and REST API development
• Familiarity with Docker, Kubernetes, Azure/AWS, and CI/CD
• Good understanding of ML/NLP fundamentals and production deployment of GenAI applications
• Good to have: LoRA/QLoRA fine-tuning, LlamaIndex, hybrid search & reranking, LangSmith/MLflow, MCP, multi-agent systems, OCR, multimodal AI

Skills Required