Threat Modeller SME - AI Safety & Risk Analysis

DeepMind Technologies Limited; New York (NY); On-site; USD 174,000 - 252,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

Google DeepMind is seeking a Threat Modeller SME for the CBRNE team to build, mature, and maintain threat models assessing dual-use risks of its advanced AI models. You will work with the Threat Modeling Lead to calibrate risk for FSF and inform safe deployment decisions.

You will apply rigorous threat intelligence to fast-paced projects, collaborate with cross-functional teams, and engage with external stakeholders including government entities and industry partners.

Qualifications

• PhD required in science/engineering/data science or equivalent practical experience.
• 3 years designing qualitative and quantitative models.
• 1 year in a national lab or similar defense/research organization.

Responsibilities

• Refine threat modeling framework and integrate into FSF review processes.
• Design evaluations identifying CBRNe risks in high-capability AI models.
• Collaborate to assess deployment safeguards for high-capability models.
• Engage with government, external partners, and experts.
• Monitor external landscape of dual-use methodologies and frontier AI.

Skills

Qualitative & quantitative modeling

National lab/defense experience

Education

PhD in Science/Engineering/Data Science

Job description

Google DeepMind is seeking a Threat Modeller SME for the CBRNE team to build, mature, and maintain threat models assessing dual-use risks of its advanced AI models. You will work with the Threat Modeling Lead to calibrate risk for FSF and inform safe deployment decisions.

You will apply rigorous threat intelligence to fast-paced projects, collaborate with cross-functional teams, and engage with external stakeholders including government entities and industry partners.