Python expert ; APIsGHA ; YAML ; build/deploy pipelines ; Docker ; AWSLLMs ; Chatbots ; OpenAI ; tool calling ; LangChain ; LangGraph ; Agentic architecture ; RAGJava ; SpringReact ; JavaScriptLLM, RAG & Agentic FrameworkKey Responsibilities:Design and implement Retrieval-Augmented Generation (RAG) pipelines using LangChain and LangGraph.Integrate AWS Open Source Vector Databases (e.g., OpenSearch with KNN plugin or other OSS-compatible vector stores).Handle complex query chaining, prompt orchestration, and data retrieval using custom agents and tools.Work on graph-based knowledge representation and retrieval using technologies like Neo4j or Stardog, or similar (preferred).Collaborate with data science and engineering teams to enable end-to-end use case delivery.Optimize performance for multi-document, multi-hop reasoning over structured/unstructured data.Required Skills:Strong hands-on experience with Python, LangChain and LangGraphExperience implementing RAG pipelines using open-source vector storesFamiliarity with Graph Databases and GraphQLGood understanding of LLMs, embeddings, and prompt engineeringExperience with AWS services (S3, Lambda, ECS/EKS, etc.)Familiarity with FastAPI or Flask for API deploymentsGood to heve Version control and DevOps exposure (Git, Docker, CI/CD pipelines)