What you'll do
- Curate/generate jailbreaks and abuse prompts
- Categorize failures; propose mitigations
- Collaborate with safety/policy mapping for rulesets
What we're looking for
- Trust & Safety/security background
- Analytical writing; taxonomy rigor
- Comfort with on‑call bursts
Where this role fits
This role sits in the AI Safety & Eval 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.