RAG Engineer – Evaluation & Optimization

About this Gig

I specialize in building production-ready Retrieval-Augmented Generation (RAG) applications that enable LLMs to answer accurately using your private data. I develop end-to-end RAG solutions with document ingestion, embeddings, vector databases, semantic search, hybrid retrieval, reranking, and LLM integration. Whether you need an AI-powered knowledge base, document Q&A system, enterprise search, or chatbot, I deliver scalable, secure, and high-performance RAG applications using Python, FastAPI, LangChain/LlamaIndex, vector databases, and cloud technologies.

Requirements

Project requirements and expected outcome Use case (chatbot, document Q&A, enterprise search, etc.) Your documents or knowledge base (PDFs, Word, websites, databases, etc.) Preferred LLM (OpenAI, Claude, Gemini, Llama, etc.), if any Preferred vector database (Pinecone, FAISS, Chroma, Weaviate, etc.), if any Deployment preference (local, cloud, AWS, Azure, GCP) Any existing application or API that needs RAG integration Timeline and any specific technical or business requirements

Related Tags