In this role, you will lead the development and optimization of cutting-edge AI solutions, focusing on large language models (LLMs), retrieval-augmented generation (RAG) systems, and advanced ranking algorithms. Build advanced matching and ranking systems using hybrid retrieval pipelines (e.g., Vespa) orchestrated in Python with LangGraph to generate Top-K candidate matches for job roles. Implement retrieval-augmented generation (RAG) pipelines integrating vector search engines such as FAISS, Pinecone, ChromaDB, or Elasticsearch. Build and deploy scalable APIs using Python frameworks like FastAPI or Flask. Expertise in vector search and RAG systems (e.g., FAISS, Pinecone, ChromaDB, Elasticsearch).