At Google DeepMind, the frontier of AI brings extraordinary opportunities—and unprecedented responsibilities. The Responsible Development and Innovation (ReDI) team operates at this intersection, including the operation of state-of-the-art measurement and evaluation of AI risks in the chemical, biological, radiological, nuclear, and explosives (CBRNe) domains.
In this critical role, you will be the operational linchpin responsible for building out, maturing, and maintaining the threat models that evaluate and support the mitigation of dual-use risks of Google DeepMind’s most advanced AI models. Your work will contribute directly into the Frontier Safety Framework (FSF), providing the rigorous risk-calibration needed to inform model releases and ensure safety-critical deployments. We need a "doer"—someone with the operational discipline to absorb vast quantities of complex scientific data, identify critical blind spots, and execute swiftly in a fast-paced environment. This is an opportunity to apply real-world threat intelligence to the vanguard of artificial intelligence safety.
Artificial intelligence will be one of humanity’s most transformative inventions. At Google DeepMind, we are a pioneering AI lab with exceptional interdisciplinary teams focused on advancing AI development to solve complex global challenges and accelerate high-quality product innovation for billions of users. We use our technologies for widespread public benefit and scientific discovery, ensuring safety and ethics are always our highest priority.
We are pushing the boundaries across multiple domains. Our global teams offer diverse learning opportunities and varied career pathways for those driven to achieve exceptional results through collective effort.
Individual pay is determined by factors including job-related skills, experience, and relevant education or training.
US: $174000 - $253000 (USD) + 15% bonus target + equity + benefits
Learn more about benefits at Google.
Responsibilities
- Refine and maintain the threat modeling framework to define critical thresholds, and integrate these 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 organizations (including the Frontier Model Forum) and external subject matter experts.
- Monitor the external engaged landscape, emerging dual-use methodologies and broader frontier AI domain.
Qualifications
Minimum qualifications:
- PhD degree in Science, Engineering, Data Science , a related field, or equivalent practical experience.
- 2 years of experience within a national laboratory, government defense organization, military intelligence unit, or specialized research institution.
Preferred qualifications:
- Experience communicating deeply complex, high-consequence technical CBRNe risks into clear, actionable insights for business leaders, corporate governance bodies, and policy experts.
- Experience executing independent projects and synthesizing large datasets under tight deadlines in fast-paced environments.
- Experience understanding complex issues through qualitative/quantitative models for decision-making with imprecise data.
- Experience red-teaming, evaluating, utilizing LLMs to identify systematic vulnerabilities and potential misuse scenarios.
- Knowledge of dual-risk components of CBRNe domains, with emphasis on biological risks and laboratory/defense paradigms.
- Track record of reviewing complex technical reports and identifying critical risks and vulnerabilities under tight timeframes.