Research Scientist, FSF Risk Modeling and Governance, DeepMind

Overview

In this role you will lead governance research and risk modeling for Google’s Frontier Safety Framework (FSF). You will drive both qualitative and quantitative analyses to assess severe AI risks and inform safeguards, collaborating with evaluation and policy teams to strengthen governance. You will manage a research team and represent the program in internal and external governance discussions, including model launch processes and safety reporting. This position combines rigorous risk modeling with governance innovation to support responsible deployment of frontier AI.

Responsibilities

• Lead research and development of the FSF, including qualitative and quantitative risk modeling
• Define pre-mitigation risk thresholds and ground empirical risk assessment work
• Collaborate with evaluation and mitigation teams to assess impact of safeguards
• Manage a team of researchers and cross-functional collaborators
• Represent the risk assessment program in internal and external governance
• Prepare external safety reports and coordinate with policy/governance teams to strengthen frontier AI governance ecosystem

Key requirements

• PhD in Economics, Philosophy, or a STEM subject, or equivalent practical experience
• 3 years of research experience in frontier AI safety or governance (e.g., threat modeling, safety frameworks, or dangerous capability/alignment evaluations)
• Ability to communicate complex technical topics to leads, governance bodies and policy experts
• Track record of driving complex projects in research settings
• Track record of applying conceptual and quantitative reasoning to uncertain research problems

• clear communicator of complex topics
• cross-functional collaboration
• project leadership
• threat modeling
• safety frameworks
• risk modeling

…