Back
Medium due to Bengaluru metro and mid-level experience, partly offset by niche RAG specialization.
High because role requires specialized retrieval, RAG, and research-corpus provenance experience.
High because the JD specifies years and mandates production RAG, embeddings, vector stores, and retriever evaluation.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Own and manage the entire retrieval pipeline for a team's private research corpus, including ingestion, chunking, embeddings, hybrid search, and reranking.
Develop dual-corpus retrieval systems integrating published literature and private institutional documents with clear provenance and citation resolution (DOI/arXiv-class).
Establish, maintain, and prove retrieval evaluation metrics and harness to demonstrate measurable quality improvements across releases.
5–8 years of experience in ML/backend engineering with production experience in Retrieval-Augmented Generation (RAG), search, or information retrieval systems.
Strong Python programming skills and hands-on experience with embeddings, vector stores, and rerankers.
Experience with retrieval quality evaluation showing measurable improvements.
Location: Bengaluru (hybrid work model).
Experienced in managing end-to-end retrieval systems within scientific or technical document corpora environments.
Skilled in building complex retrieval solutions involving multiple corpora with provenance and citation accuracy.
Demonstrates rigorous evaluation and metric-driven improvement methodology for retrieval systems.