Biologist

Highlights

• Evaluate frontier AI models to prevent misuse for harmful biological agents.
• Design biology evaluations and red-teaming strategies for Gemini safety.
• Help shape Google’s CBRNE safety policy for responsible frontier AI.

Ideal candidate

A wet-lab biologist with deep biosecurity intuition who cares about ensuring powerful AI accelerates science without enabling harm. You enjoy red-teaming, translating complex risks into policy, and collaborating across science and AI safety.

Requirements

• PhD in Wet-Lab Virology, Microbiology, Biology, or related field or equivalent practical experience
• 3 years of wet-lab experience with dual-use research, high-consequence pathogens, or biological toxins
• Experience utilizing LLMs or narrow-use AI models to analyze and mitigate biological risks
• Authored peer-reviewed publications in microbiology, virology, host-pathogen interactions, protein biochemistry, or immunology
• Experience in AI safety, evaluations, red-teaming, or applied AI research
• Experience using command line tools or coding
• Proven application of biosecurity and biosafety concepts including identifying misuse scenarios of emerging technologies
• Knowledge of biological weapons challenges, threat landscape, mitigations and relevant stakeholders
• Knowledge of microbiology/virology intersection with AI safety and Safety Frameworks
• Active security clearance or eligibility to obtain and maintain one