What you'll do
- Curate and version prompt variants with metadata
- Run A/B eval experiments and track results
- Maintain prompt library with clear documentation
- Collaborate on prompt optimization strategies
What we're looking for
- Prompt engineering experience
- Eval framework literacy
- Git workflow comfort
- Strong written communication
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.