Threat Modeling SME - AI Safety & CBRNE Risk Expert

DeepMind Technologies Limited; Greater London; Presencial; GBP 131.000 - 190.000; Jornada completa

Descripción de la vacante

Google DeepMind seeks a Threat Modeller SME in the CBRNE team to build, mature, and maintain threat models that evaluate dual-use risks of its AI models. You will work with the Threat Modeling Lead to support FSF review processes and deployment decisions, translating complex data into actionable risk insights.

You will collaborate across evaluation and mitigation teams, engage with government entities and external stakeholders, and help ensure safety and ethics are central to releases and

Formación

• PhD in Science, Engineering, Data Science or equivalent practical experience.
• 3 years of experience designing qualitative and quantitative models.
• 1 year of experience working within a national laboratory, research organization, government defense organization, military intelligence unit, or specialized research organization.

Responsabilidades

• Refine and maintain the threat modeling framework to define critical thresholds, and integrate models into FSF review processes to support deployment decision-making.
• Partner cross-functionally to design and implement evaluations identifying CBRNe-related risks in high-capability AI models.
• Collaborate across evaluation and mitigation teams to determine if deployment safeguards are adequate for high-capability models.
• Engage with external stakeholders, including governmental entities, third-party organisations (including the Frontier Model Forum) and subject matter experts.
• Monitor the external competitor landscape, emerging dual-use methodologies and broader frontier AI domain.

Conocimientos

Qualitative and quantitative modeling

Threat modelling framework

LLM red-teaming

High-consequence risk communication

Educación

PhD in Science, Engineering, Data Science or equivalent

Descripción del empleo

Google DeepMind seeks a Threat Modeller SME in the CBRNE team to build, mature, and maintain threat models that evaluate dual-use risks of its AI models. You will work with the Threat Modeling Lead to support FSF review processes and deployment decisions, translating complex data into actionable risk insights.

You will collaborate across evaluation and mitigation teams, engage with government entities and external stakeholders, and help ensure safety and ethics are central to releases and