Threat Modeler Lead, Chemical, Biological, Radiological, Nuclear, and Explosives

London, UK

• In this role, you'll build out and maintain threat models evaluating dual-use risks of advanced AI models in CBRNe domains.
• Refine threat modelling frameworks and integrate critical thresholds into Frontier Safety Framework review processes.
• Design and implement evaluations identifying CBRNe-related risks in high-capability AI models.
• Collaborate with evaluation and mitigation teams to assess deployment safeguard adequacy for advanced models.
• Engage with external stakeholders and monitor emerging dual-use methodologies in frontier AI.

Google DeepMind is a frontier AI research and product company, with teams working on alignment, policy, and security. We post specific opportunities at Google DeepMind that we think may be high impact. We do not necessarily recommend working at other positions at Google DeepMind. You can read concerns about doing harm by working at a frontier AI company in our career review on the topic.