Threat Modeler, Preparedness

Details

About the Team

The Preparedness team is part of the Safety Systems org at OpenAI and is guided by OpenAI’s Preparedness Framework. The team monitors and predicts the evolving capabilities of frontier AI systems with an eye toward misuse risks whose impact could be catastrophic. The team identifies, tracks, and prepares for catastrophic risks related to frontier AI models and ensures concrete procedures, infrastructure, and partnerships to mitigate these risks and safely handle development of powerful AI systems. Preparedness connects capability assessment, evaluations, internal red teaming, and mitigations for frontier models, and coordinates on AGI preparedness.

About the Role

As a threat modeler, you will own OpenAI’s holistic approach to identifying, modeling, and forecasting frontier risks from frontier AI systems. You will ensure evaluation frameworks, safeguards, and taxonomies are robust, high-coverage, and forward-looking. You will shape the rationale for prioritizing and mitigating risks across domains and serve as a central node connecting technical, governance, and policy perspectives.

Responsibilities

• Develop and maintain comprehensive threat models across misuse areas (bio, cyber, attack planning, etc.).
• Develop plausible and convincing threat models for loss of control, self-improvement, and other alignment risks from frontier AI systems.
• Forecast risks by combining technical foresight, adversarial simulation, and emerging trends.
• Pair closely with technical partners on capability evaluations to ensure coverage of severe risks differentially enabled by frontier AI systems.
• Pair closely with Bio and Cyber Leads to size remaining risk of designed safeguards and translate threat models into actionable mitigation designs.
• Act as thought partner and explainer of “why” and “when” for high-investment mitigation efforts, helping stakeholders understand rationale behind prioritization.
• Serve as the central node connecting technical, governance, and policy perspectives on misuse risk prioritization and focus.

Requirements

• Deep experience in threat modeling, risk analysis, or adversarial thinking (e.g., security, national security, or safety).
• Strong grasp of AI alignment literature and understanding of risks from frontier AI systems.
• Knowledge of how AI evaluations work and ability to connect evaluation results to capability testing and safeguard sufficiency.
• Experience working across technical and policy domains to drive multidisciplinary risk assessments.
• Ability to communicate complex risks clearly to both technical and non-technical audiences.
• Systems thinking and anticipation of second-order and cascading risks.

Benefits and Compensation

• Base pay listed: $325K (total compensation also includes equity and potential performance-related bonuses).
• Medical, dental, and vision insurance with employer contributions to Health Savings Accounts.
• Pre-tax accounts for Health FSA, Dependent Care FSA, and commuter expenses.
• 401(k) with employer match.
• Paid parental, medical, and caregiver leave.
• Flexible PTO and paid company holidays/closures.
• Mental health and wellness support; employer-paid basic life and disability coverage.
• Annual learning and development stipend.
• Daily meals in offices and meal delivery credits as eligible.
• Relocation support for eligible employees.

About OpenAI

OpenAI is an AI research and deployment company dedicated to ensuring general-purpose artificial intelligence benefits all of humanity. The company emphasizes safety and diverse perspectives. OpenAI is an equal opportunity employer and provides reasonable accommodations to applicants with disabilities.