Threat Modeling Lead: Harmful Manipulation & AI Safety

DeepMind Technologies Limited; Mountain View (CA); On-site; USD 207,000 - 300,000; Full time

Job summary

Google DeepMind’s Responsible Development and Innovation (ReDI) team seeks a threat intel professional to develop and maintain threat models, monitor emerging manipulation tactics, and translate threats into actionable analyses guiding safety thresholds.

You’ll conduct technical investigations, design evaluations of Harmful Manipulation, and collaborate across teams to ensure safeguards for frontier AI. Mountain View, CA based with flexible working options.

Qualifications

• PhD or equivalent experience in relevant fields.
• Experience with data collection, scraping, log analysis.
• Experience evaluating manipulation, persuasion, or influence operations.

Responsibilities

• Refine and maintain Harmful Manipulation threat models 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 (including the Frontier Model Forum) and external subject matter experts.
• Monitor the external competitor landscape, emerging dual-use methodologies and broader frontier AI domain.

Skills

Technical experience

OSINT data collection

Data analysis

Education

PhD degree in Computer Science or related field

Job description

Google DeepMind’s Responsible Development and Innovation (ReDI) team seeks a threat intel professional to develop and maintain threat models, monitor emerging manipulation tactics, and translate threats into actionable analyses guiding safety thresholds.

You’ll conduct technical investigations, design evaluations of Harmful Manipulation, and collaborate across teams to ensure safeguards for frontier AI. Mountain View, CA based with flexible working options.