AI Enterprise Search Relevance Tuning Lead

Quelion Intelligence

Remote · $160k – $200k / year · Full-time · Posted 2 months ago

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

About the role

The models you'll ship will be used by knowledge workers at hundreds of enterprise customers every time they search their internal wikis, tickets, and contracts. We need a lead who can own relevance end to end: retrieval quality, reranking, and the RAG pipeline that turns search results into grounded answers. You'll set the technical direction for how we evaluate relevance across dozens of customer document sets that look nothing alike, and you'll have the final call on tradeoffs between latency, cost, and answer quality. This is a hands-on lead role — you'll be writing code and reviewing architecture in the same week.

Fully remote.

Responsibilities

Set technical direction for retrieval, reranking, and RAG answer generation
Own the relevance evaluation framework used across all customer deployments
Review architecture decisions from the broader search and NLP team
Partner with customer engineering to diagnose relevance regressions on live accounts

Requirements

Deep hands-on experience building production RAG systems with LangChain or similar
Strong understanding of retrieval and reranking tradeoffs at enterprise scale
Comfortable deploying and debugging containerized services with Docker
Experience leading technical direction on a small, senior team