What you'll do
- Judge retrieval relevance against source passages
- Write clear rationales for each judgment
- Maintain and refresh gold-set examples
- Collaborate on consensus rules and edge cases
What we're looking for
- RAG or search relevance experience
- Strong analytical and writing skills
- Taxonomy and labeling comfort
Where this role fits
This role sits in the LLM Infra & MLOps TalentZone and commonly supports packs like Cost & Quality Sprint and Guardrail & Reg Audit. Work is routed under QA; this is a managed bench, not a marketplace.