Senior RAG Engineer / Technical Lead for Healthcare AI Project

We are looking for an experienced RAG Engineer / Technical Lead to design and implement a Retrieval-Augmented Generation solution for a healthcare client. This is a hands-on leadership role. The selected professional will take ownership of the technical design, architecture decisions, implementation, evaluation, and production readiness of the solution. The system will retrieve information from healthcare documents and enterprise data sources and generate accurate, traceable, and source-grounded responses using large language models. What you will work on - Lead the end-to-end design and implementation of the RAG solution - Design document ingestion and processing workflows - Define chunking, metadata, indexing, and document versioning strategies - Select suitable embedding models, reranking models, vector databases, and LLMs - Implement semantic search, keyword search, hybrid retrieval, and metadata filtering - Improve retrieval quality through query rewriting, reranking, and context optimization - Implement source citations and response traceability - Develop safeguards to reduce hallucinations and unsupported responses - Build evaluation workflows for retrieval accuracy, answer quality, faithfulness, latency, and cost - Design APIs and backend services for the RAG platform - Support deployment, monitoring, logging, and production optimization - Implement access controls and security measures for sensitive healthcare information - Work closely with engineering, product, security, and healthcare-domain stakeholders - Review implementation quality and guide other engineers involved in the project What we are looking for - Strong hands-on experience designing and implementing production RAG systems - Excellent Python and backend engineering skills - Experience with LangChain, LangGraph, LlamaIndex, Haystack, or custom RAG frameworks - Experience with Elasticsearch, OpenSearch, Pinecone, Weaviate, Qdrant, Milvus, pgvector, or similar technologies - Strong knowledge of embeddings, hybrid search, reranking, query rewriting, metadata filtering, and - retrieval evaluation - Experience processing PDFs, Word documents, databases, APIs, and enterprise data sources - Experience deploying LLM applications on AWS, Azure, or GCP - Ability to lead architecture and technical design while remaining hands-on with implementation - Strong communication, documentation, and stakeholder-management skills - Experience with healthcare data, PHI, HIPAA-sensitive systems, clinical information, or other regulated environments is preferred