What you'll do
- Experiment with routing policies for win‑rate and cost
- Author/trim prompts; maintain prompt libraries with versioning
- Integrate eval harnesses; set guardrails and roll‑back paths
What we're looking for
- Hands‑on with LLM APIs and routers
- Strong experimentation habits and metrics literacy
- Git‑native workflow (PRs, code reviews)
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.