Threat Modeler

Responsibilities

• Develop and maintain comprehensive threat models across misuse areas including bio, cyber, and attack planning
• Develop plausible threat models regarding loss of control, self-improvement, and other alignment risks
• Forecast risks by combining technical foresight, adversarial simulation, and emerging trends
• Partner with technical teams on capability evaluations to ensure coverage of severe risks
• Collaborate with Bio and Cyber Leads to size remaining risk and translate models into mitigation designs
• Act as a thought partner to explain the rationale behind high-investment mitigation efforts
• Connect technical, governance, and policy perspectives regarding misuse risk prioritization

Requirements

• Deep experience in threat modeling, risk analysis, or adversarial thinking (e.g., security, national security, or safety)
• Strong understanding of risks from frontier AI systems and AI alignment literature
• Knowledge of how AI evaluations work and how to connect results to capability testing
• Ability to communicate complex risks clearly to both technical and non-technical audiences
• Systems thinking approach to anticipate second-order and cascading risks

About the Company

OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity. We push the boundaries of the capabilities of AI systems and seek to safely deploy them to the world through our products.