Threat Modeler Lead, CBRNE, DeepMind

Threat Modeler Lead, CBRNE, DeepMind Overview

At Google DeepMind, we are at the cutting edge of artificial intelligence, where we face both remarkable opportunities and significant responsibilities. The Responsible Development and Innovation (ReDI) team is dedicated to assessing and managing AI risks in the chemical, biological, radiological, nuclear, and explosives (CBRNe) domains. We are seeking a Threat Modeler Lead who will play a crucial role in developing and maintaining threat models that evaluate and mitigate dual-use risks associated with our advanced AI models.

In this pivotal position, you will contribute to the Frontier Safety Framework (FSF), ensuring that our model releases are rigorously calibrated for safety-critical deployments. We are looking for a proactive individual who can process extensive scientific data, pinpoint critical blind spots, and act decisively in a fast-paced environment. This role offers a unique chance to apply real-world threat intelligence to enhance AI safety.

Responsibilities

• Refine and sustain the threat modeling framework to establish critical thresholds and integrate these models into the 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 with 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, and subject matter experts, to gather insights and feedback.
• Monitor the evolving landscape of dual-use methodologies and broader issues within the frontier AI domain.

Requirements

• A PhD in Science, Engineering, Data Science, or a related field, or equivalent practical experience.
• At least 2 years of experience in a national laboratory, government defense organization, military intelligence unit, or specialized research institution.
• Proven ability to communicate complex technical CBRNe risks into clear, actionable insights for business leaders and policy experts.
• Experience in managing independent projects and synthesizing large datasets under tight deadlines in dynamic environments.
• Ability to analyze complex issues using qualitative and quantitative models for decision-making with uncertain data.
• Experience in red-teaming and utilizing large language models (LLMs) to identify systematic vulnerabilities and potential misuse scenarios.
• Knowledge of dual-risk components in CBRNe domains, particularly focusing on biological risks and defense/laboratory paradigms.
• A strong track record of reviewing complex technical reports to identify critical risks and vulnerabilities under 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 meaningful work that contributes to public benefit and scientific discovery.

Degree Requirement: Bachelor’s

Visa Sponsorship May be