AI Biology Safety Scientist & Model-Risk SME

Google LLC; Mountain View (CA); On-site; USD 174,000 - 252,000; Full time

Job summary

Google DeepMind invites applications from qualified biologists/microbiologists for a Research Scientist SME role in the CBRNE team within RFAIR, Mountain View, CA. You will lead model evaluation, mitigation design, and cross-functional collaboration to prevent misuse while advancing scientific utility, with emphasis on safety policy and external communication.

Applicants will work on harmful biological agents, dual-use risks, and AI safety frameworks, contributing to responsible frontier AI

Qualifications

• PhD in wet-lab virology, microbiology, biology, or equivalent practical experience.
• 3 years of wet-lab experience with dual-use research, consequence pathogens, or biological toxins.
• Experience across microbiology, virology, host-pathogen interactions, protein biochemistry, or immunology, evidenced by peer-reviewed publications or equivalent.
• Experience applying biosecurity and biosafety concepts, including identifying misuse scenarios of emerging technologies.
• Experience utilizing LLMs or narrow-use AI models to analyze and mitigate biological risks.

Responsibilities

• Test, evaluate, and mitigate harmful capabilities of frontier AI models in the biology domain.
• Design, develop, and execute biology evaluations, assessments, frameworks, and red-teaming strategies to test the capability, safety, and uplift of AI models and support the development of mitigations.
• Collaborate with CBRNE/responsibility engineers to ensure blocks on harmful outputs without overly degrading the model's scientific utility, requiring a deep understanding of dual-use science.
• Partner with experts in various fields of CBRN, science, AI ethics, policy, and safety.
• Support the ongoing development and refinement of Google's CBRNE safety policy, and clearly communicate complex risks, evaluation findings, and mitigation strategies to leadership and technical and non-technical external stakeholders.

Skills

Biosecurity concepts

AI safety

Cross-functional collaboration

Technical communication

Biology domain knowledge

Education

PhD in virology/microbiology/biology

Equivalent practical experience

Tools

Command line tools

Coding

Job description

Google DeepMind invites applications from qualified biologists/microbiologists for a Research Scientist SME role in the CBRNE team within RFAIR, Mountain View, CA. You will lead model evaluation, mitigation design, and cross-functional collaboration to prevent misuse while advancing scientific utility, with emphasis on safety policy and external communication.

Applicants will work on harmful biological agents, dual-use risks, and AI safety frameworks, contributing to responsible frontier AI