Job Description

Minimum qualifications

• PhD in Computational Biology, Bioinformatics, Biochemistry, Microbiology, or a related field or equivalent practical experience.
• Experience applying computational tools, biological modeling, and command-line scripts to analyze protein biochemistry, microbiology, or pathogenic systems.
• Experience working with biological datasets (e.g., genomics, proteomics, structural biology).
• Experience evaluating emerging technologies and assessing potential biorisk or misuse scenarios.
• Experience with peer-reviewed contributions and working across cross-functional teams.
• Experience supporting a secure, global research environment.

Preferred qualifications

• Experience working in AI safety, evaluations, red-teaming, or applied AI research at a national laboratory, academic institution, or industry setting.
• Knowledge of challenges of biological weapons, the biological threat landscape, potential mitigations and awareness of relevant stakeholders.
• Familiarity with agentic AI and its applicability to frontier risk within biology.
• Understanding of Safety Frameworks in AI. Knowledge of the intersection of microbiology/virology within AI safety.
• Intuition and creativity for how frontier AI models or agents could enhance these capabilities and lower barriers for bad actors.
• Active security clearance, or the eligibility to obtain and maintain one.

About the job

Google’s CBRNE team (Chemical, Biological, Radiological, Nuclear and Explosives) makes sure that as Gemini gets better at science, it does not become a tool for catastrophic harm. We would like to invite applications from qualified computational biologists for the position of a Computational Biologist Subject Matter Expert (SME) in the CBRNE team within the Responsible Frontier AI Research (RFAIR) team, joining SMEs with broad experience across biology.

In this role, you will be hired for a Research Scientist position serving as a technical expert responsible for evaluating and mitigating safety risks of frontier AI models (primarily but not limited to LLMs) in the biology domain; specifically, model assistance in the acquisition, development and dissemination of harmful biological agents and other dual use entities.

Artificial intelligence will be one of humanity’s most transformative inventions. At Google DeepMind, we are a pioneering AI lab with exceptional interdisciplinary teams focused on advancing AI development to solve complex global challenges and accelerate high-quality product innovation for billions of users. We use our technologies for widespread public benefit and scientific discovery, ensuring safety and ethics are always our highest priority.

We are pushing the boundaries across multiple domains. Our global teams offer diverse learning opportunities and varied career pathways for those driven to achieve exceptional results through collective effort.

Individual pay is determined by factors including job-related skills, experience, and relevant education or training.

US: $174000 - $252000 (USD) + 15% bonus target + equity + benefits

Learn more about benefits at Google.

In this role, you will be hired for a Research Scientist position serving as a technical expert responsible for evaluating and mitigating safety risks of frontier AI models (primarily but not limited to LLMs) in the biology domain; specifically, model assistance in the acquisition, development and dissemination of harmful biological agents and other dual use entities.

We are pushing the boundaries across multiple domains. Our global teams offer diverse learning opportunities and varied career pathways for those driven to achieve exceptional results through collective effort.

Responsibilities

• Develop assessments and frameworks to rigorously quantify capability thresholds, technical feasibility, and potential consequences of model uplift wherever possible.
• Design and execute robust evaluations and relevant datasets of computational biology and/or microbiology and other critical related areas. The goal of these evaluations is to elicit the maximum capability of the model to determine how it can uplift malicious actors across the domain.
• Partner with responsibility engineers to design highly nuanced mitigations that block harmful outputs without overly degrading the model's scientific utility. Similar to writing capability evaluations, this requires a deep understanding of dual use science.
• 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.