Research Scientist, Gemini Safety and Behavior, DeepMind

New York, NY, USA; Mountain View, CA, USA; London, UKFull Time$207K – $300K/yr AI Safety

GeminiLLM safetyred teamingalignment

Job Description

The Alignment and Reliability role develops auditing frameworks, defensive safeguards, toolsets, and autonomous agents for Google DeepMind foundation systems. It drives safety and security jailbreak research, red and blue teaming of multimodal and agentic GenAI, and deployable mitigations.

Opens the verified employer application page.

Job Details

Posted: September 26, 2026
Expires: October 26, 2026
Views: 4
Applies: 1

About the Company

Google DeepMind

London, UK

Google DeepMind is a world-leading AI research lab building AI systems that can think and act to advance science and benefit humanity.

Research Scientist, Gemini Safety and Behavior, DeepMind

Google DeepMind