Description :

We are hiring a specialist FDE focused on Search, Retrieval, and RAG-based AI systems. This role requires deep expertise in LLM grounding, semantic search, and retrieval optimization.

Key Responsibilities :

- Design and optimize RAG pipelines for enterprise applications

- Implement hybrid search (BM25 + dense retrieval)

- Work with vector databases (Pinecone, ChromaDB)

- Improve retrieval accuracy using rerankers and evaluation frameworks

- Build scalable backend systems for search-heavy use cases

- Collaborate with enterprise clients on knowledge systems

Must-Have Skills (STRICT) :

- Strong hands-on experience with RAG (MANDATORY)

- Experience with vector databases (Pinecone / ChromaDB)

- Knowledge of hybrid search and ranking systems

- Backend development (Python, APIs, FastAPI)

- Experience with prompt engineering and retrieval tuning

Mandatory Experience :

- Built RAG-based systems in production environments

- Experience improving LLM accuracy using retrieval techniques

- Exposure to evaluation frameworks (RAGAS or similar preferred)