Threat Modeling Lead, Harmful Manipulation

As part of the Responsible Development and Innovation (ReDI) team, you will work at the critical intersection of threat intelligence, model behaviour, and risk assessment. You will be responsible for developing and maintaining robust threat models, keeping abreast of emerging bad actors and tactics and translating the threat landscape into actionable analyses. Your work will range from conducting technical investigations to designing evaluations to probe how DeepMind's most advanced AI models interact with and influence users. Your insights will directly shape deployment safeguards and define critical safety launch thresholds. You will have an opportunity to apply real-world threat intelligence to the vanguard of frontier artificial intelligence safety.

If you are driven by the mission to protect the global digital ecosystem from scaled AI misuse and manipulation, this role will empower you to make a tangible, high-stakes impact.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 varied learning opportunities and 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: $207000 - $300000 (USD) + 20% bonus target + equity + benefits

Learn more about benefits at Google. Note: By applying to this position you will have an opportunity to share your preferred working location from the following: New York, NY, USA; London, UK; Mountain View, CA, USA.

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