Threat Modeler Lead, CBRNE, DeepMind
Threat Modeler Lead, CBRNE, DeepMind Overview
| Company Name | |
| Job Role | Threat Modeler Lead, CBRNE, DeepMind |
| Qualifications | Bachelor’s |
| Category | General Jobs |
| Job Type | Full Time |
| Location | London |
At Google DeepMind, the intersection of artificial intelligence and responsibility presents unique opportunities. The Responsible Development and Innovation (ReDI) team is dedicated to evaluating AI risks in the chemical, biological, radiological, nuclear, and explosives (CBRNe) domains. As the Threat Modeler Lead, you will play a crucial role in developing and maintaining threat models that assess and mitigate dual-use risks associated with Google DeepMind’s advanced AI models.
Your contributions will directly impact the Frontier Safety Framework (FSF), ensuring rigorous risk calibration to inform model releases and safety-critical deployments. We seek a proactive individual capable of processing complex scientific data, identifying critical blind spots, and executing tasks efficiently in a fast-paced environment. This position allows you to apply real-world threat intelligence to enhance AI safety.
Responsibilities
- Enhance and sustain the threat modeling framework to establish critical thresholds and incorporate these models into the Frontier Safety Framework (FSF) review processes to aid in deployment decision-making.
- Collaborate with cross-functional teams to design and execute evaluations that identify CBRNe-related risks in advanced AI models.
- Work alongside evaluation and mitigation teams to assess whether deployment safeguards are sufficient for high-capability models.
- Engage with external stakeholders, including government bodies, third-party organizations like the Frontier Model Forum, and subject matter experts.
- Stay informed about the external landscape, emerging dual-use methodologies, and developments in the frontier AI domain.
Requirements
- Possess a PhD in Science, Engineering, Data Science, or a related field, or have equivalent practical experience.
- Have at least 2 years of experience working in a national laboratory, government defense organization, military intelligence unit, or specialized research institution.
- Demonstrate the ability to communicate complex technical CBRNe risks into clear, actionable insights for business leaders and policy experts.
- Show experience in managing independent projects and synthesizing large datasets under tight deadlines in dynamic environments.
- Exhibit proficiency in understanding complex issues through qualitative and quantitative models for decision-making with uncertain data.
- Have experience in red-teaming and evaluating the use of large language models (LLMs) to identify systematic vulnerabilities and potential misuse scenarios.
- Possess knowledge of dual-risk components within CBRNe domains, particularly focusing on biological risks and laboratory/defense paradigms.
- Have a proven track record of reviewing complex technical reports and identifying critical risks and vulnerabilities within tight time constraints.
Benefits
- Opportunity to work at the forefront of AI development and safety.
- Access to diverse learning opportunities and varied career pathways.
- Engagement in a culture that prioritizes safety and ethics in AI.
Degree Requirement: Bachelor’s
Visa Sponsorship May be
To apply for this job please visit www.google.com.