← Back to all jobs

Google DeepMind logo

Research Scientist, Gemini Safety and Behaviour

Google DeepMind

Job AI safety & policy

Where
Work mode not stated: New York / Mountain View / London · USA, UK
Level
Mid career, 5–9 yrs
Pay
$207k–$300k, top of range above $100k a year$207,000 – $300,000
Apply by
Rollingposted 24 Sep
Hours and type
Full-time
Kind of work
Research
Added to CFI
24 September 2026
Network
LinkedIn

About the role

Research and build mitigations for jailbreaks and abuse risks in Gemini models, including red and blue teaming of text, multimodal and agentic systems. Works with product teams to deploy fixes at scale.

Summary of the employer's page written by AI. Check the full listing before you apply.

Requires

PhD in computer science or equivalent experience; 2 years in LLM safety or security

Apply on employer site