Member of Technical Staff, Search Ranking

Parallel Web Systems•Bay Area, CA

9d•$150,000 - $300,000•Onsite

About The Position

You will own the multi-stage ranking pipeline that narrows a web-scale set of candidates down to the handful of best passages for a query, spending the least compute necessary to do it well. You will push precision and recall across fast candidate retrieval, lightweight first-pass ranking, and heavier neural reranking, decide how much compute each query deserves, and grade everything on real usage outcomes rather than offline proxies.

Requirements

Deep intuition for relevance, feature engineering, and the trade-offs between quality, latency, and cost.
Think rigorously about how ranking, retrieval, and agent behavior inform one another, and how to train models that serve all three.
Care about your research being applied to product and systems that millions use.

Responsibilities

Own the multi-stage ranking pipeline that narrows a web-scale set of candidates down to the handful of best passages for a query, spending the least compute necessary to do it well.
Push precision and recall across fast candidate retrieval, lightweight first-pass ranking, and heavier neural reranking.
Decide how much compute each query deserves.
Grade everything on real usage outcomes rather than offline proxies.