Be responsible to 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 communicating complex risks, evaluation findings, and mitigation strategies to leadership and technical and non-technical external stakeholders.
Minimum qualifications
PhD in Wet-Lab Virology, Microbiology, Biology, or a 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 across microbiology, virology, host-pathogen interactions, protein biochemistry, or immunology.
Preferred qualifications
Experience working in AI safety, evaluations, red-teaming, or applied AI research at a national laboratory, academic institution, or industry setting.
Experience in using command line tools or coding.
Proven application of biosecurity and biosafety concepts, including identifying misuse scenarios of emerging technologies.
Knowledge of challenges of biological weapons, the biological threat landscape, potential mitigations and awareness of relevant stakeholders.
Knowledge of the intersection of microbiology/virology within AI safety and Safety Frameworks in AI.
Active security clearance, or the eligibility to obtain and maintain one.
PhD in Wet-Lab Virology, Microbiology, Biology, or a 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 across microbiology, virology, host-pathogen interactions, protein biochemistry, or immunology.
