Skills : Python, PyTorch, Rest Api,
Specializes in retrieval-augmented generation architecture — building the search, indexing, and retrieval layer that grounds LLM outputs in accurate, up-to-date information.
Job Description:
Specializes in retrieval-augmented generation architecture — building the search, indexing, and retrieval layer that grounds LLM outputs in accurate, up-to-date information.
Key Skills:
- Vector databases and embeddings (Pinecone, Weaviate, FAISS, pgvector)
- Search relevance/ranking, hybrid search (keyword + semantic)
- Data pipeline engineering for document ingestion and chunking
- Evaluation of retrieval quality (precision/recall, relevance scoring)
- API design for retrieval services
Experience Required:
- 2–5 years in search/information retrieval, data engineering, or backend engineering
- Direct RAG system experience strongly preferred