jobs
Senior AI Safety Researcher
The AI Safety Protections team within Trust and Safety develops and implements cutting-edge AI-powered solutions to ensure the safety of foundation models, inclduing Gemini, Nano Banana, Veo, Agents…
Em inglês
- Company
- Location
- Mountain View, CA, USA
- Status
- Closed
- Posted
- 2026-10-06 09:09 UTC
Google's AI Safety Protections team, part of Trust and Safety, is hiring a senior researcher to work on safeguards for foundation models including Gemini, Veo, agents and robotics. The role sits between research, model development and policy: turning threat models into evaluations, mitigations and launch decisions, and applying ML and statistical methods to test protections. It asks for five years in data analysis or data science, programming (Python, C/C++, Java) and SQL, with LLM prompt engineering, fine-tuning and trust-and-safety experience preferred. Work may involve graphic or upsetting content.
Original job posting