Threat Modeling Lead: Guarding AI from Harmful Manipulation

Google LLC; New York (NY); Hybrid; USD 207,000 - 300,000; Full time

Job summary

DeepMind, part of Google, is seeking a Share Threat Modeling Lead within the Responsible Development and Innovation team. You will build and maintain threat models, identify Harmful Manipulation risks, and translate findings into actionable safeguards for frontier AI models.

Based in New York, London, or Mountain View, you will collaborate with cross-functional partners and engage with external stakeholders to shape deployment decisions and safety thresholds at scale.

Qualifications

• PhD degree in Computer Science, Political Science, Psychology, Computational Social Science, a related field, or equivalent industry experience.
• Experience performing technical work; for example, OSINT data collection, API scraping, log analysis, and other data analysis.
• Experience studying, tracking, or evaluating the mechanics of human manipulation, persuasion, propaganda, influence operations, social engineering, or a related social phenomena.

Responsibilities

• Refine and maintain Harmful Manipulation threat modeling frameworks to define critical thresholds, and integrate these models into Google's Frontier Safety Framework risk determination processes to support deployment decision-making.
• Partner cross-functionally to design and implement evaluations identifying Harmful Manipulation-related capabilities and risks, publish on novel methodologies and capabilities insights.
• Collaborate across evaluation and mitigation teams to determine if deployment safeguards are adequate for high-capability models.
• Engage with external research community and stakeholders including governmental entities, national safety institutes, third-party organisations and external subject matter experts.
• Monitor the external competitor landscape, emerging dual-use methodologies and broader frontier AI domain.

Skills

Threat modeling

OSINT data collection

Log analysis

Data analysis

Education

PhD or equivalent experience

Job description

DeepMind, part of Google, is seeking a Share Threat Modeling Lead within the Responsible Development and Innovation team. You will build and maintain threat models, identify Harmful Manipulation risks, and translate findings into actionable safeguards for frontier AI models.

Based in New York, London, or Mountain View, you will collaborate with cross-functional partners and engage with external stakeholders to shape deployment decisions and safety thresholds at scale.