Staff Engineering Analyst, Trust and Safety RAI Testing, Scaled Testing

Define and advocate the Trust and Safety (T&S) RAI SCALE technical roadmap, establishing North Star metrics and automated governance to accelerate Google-wide launch velocity. Direct the research-to-operations architecture translating high-risk 0-to-1 evaluations (multi-turn, agentic, frontier safety) into production-ready pipelines. Lead cross-organizational gap analyses with GDM/PAs, defining statistical standards and scaling high-precision LLM-as-a-judge autoraters.

Architect unified data pipelines and telemetry unifying pre-launch testing and post-launch monitoring to automate executive risk attestations. Serve as the final decision-maker on critical GenAI safety escalations, align executive leadership, and mentor executive Engineering Analysts. Work with sensitive content or situations and may be exposed to graphic, controversial, or upsetting topics or content.