Technical Policy Manager, Cyber Harms

ABOUT ANTHROPIC

Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems.

ABOUT THE ROLE

We are looking for a cybersecurity expert to lead our efforts to prevent AI misuse in the cyber domain. As a Cyber Harms Technical Policy Manager, you will lead a team applying deep technical expertise to inform the design of safety systems that detect harmful cyber behaviors and prevent misuse by sophisticated threat actors. Working closely with Research Engineers who build these safety systems, you and your team will provide the critical cybersecurity domain knowledge needed to ensure our safeguards are effective against real-world threats. You will be at the forefront of defining what responsible AI safety looks like in the cybersecurity domain, working across research, policy, and engineering to translate complex cyber threat concepts into concrete technical safeguards and actionable policies. This is a unique opportunity to shape how frontier AI models handle dual-use cybersecurity knowledge—balancing the tremendous potential of AI to advance legitimate security research and defensive capabilities while preventing misuse by malicious actors.

IN THIS ROLE, YOU WILL

• Lead and grow a team of technical specialists focused on cyber threat modeling and evaluation frameworks
• Design and oversee execution of capability evaluations ("evals") to assess the cyber-relevant capabilities of new models
• Create comprehensive cyber threat models, including attack vectors, exploit chains, precursor identification, and weaponization techniques
• Develop and iterate on usage policies that govern responsible use of our models for emerging capabilities and use cases related to cyber harms
• Serve as the primary domain expert on cyber harms, advising cross-functional teams on threat landscapes and mitigation strategies
• Collaborate closely with internal and external threat modeling experts to develop training data for safety systems, and with ML engineers to train these systems, optimizing for both robustness against adversarial attacks and low false-positive rates for legitimate security researchers
• Analyze safety system performance in traffic, identifying gaps and proposing improvements