Back
Mid-level Bengaluru role with common 'AI Engineer' title and broad RAG skill requirements increases applicant competition.
Requires specialized RAG, scientific-corpus, and vector-store expertise, limiting cross-industry transferability.
Explicit 5–8 year requirement plus mandatory production RAG, embeddings, and backend skills enforces strict filters.
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 including document ingestion, chunking, embeddings, hybrid search, and reranking.
Build and maintain dual-corpus retrieval systems combining published literature and private institutional documents with provenance and citation resolution.
Develop and manage retrieval evaluation processes including building the evaluation harness, defining metrics, and demonstrating measurable improvement release over release.
5–8 years of relevant experience in ML/backend engineering with production RAG, search, or IR systems.
Strong proficiency in Python with hands-on experience using embeddings, vector stores, and rerankers.
Experience in retrieval evaluation with clear evidence of measuring and improving retrieval quality.
Location requirement: Bengaluru (hybrid).
Experienced in end-to-end retrieval systems specifically involving research or technical document corpora.
Skilled in managing complex multi-source information pipelines including citation and identifier resolution (e.g., DOI/arXiv).
Demonstrates strong rigor in evaluation and continuous improvement of retrieval quality over multiple releases.