Threat Modeler, Preparedness

OpenAI • San Francisco, CA

2d • $325,000 - $325,000

About The Position

Preparedness is a critical Safety Research team at OpenAI, which is focused on mitigating AI threats that could scale to an extreme level of severity. Our work involves: Tracking and prediction. Monitoring and predicting the evolving misalignment propensities and capabilities of frontier AI systems. Mitigation. Keeping misuse safeguards, alignment tools, and security measures on track to adequately address extreme threats that might arise in the future. Coordination. Setting mitigation targets by maintaining OpenAI’s preparedness framework, and partnering with other staff to achieve these targets. This is urgent, fast-paced work that has far-reaching implications for the company and for society.

As a threat modeler, you will own OpenAI’s holistic approach to identifying, modeling, and forecasting frontier risks from frontier AI systems. This role ensures that our evaluation frameworks, safeguards, and taxonomies are robust, high-coverage, and forward-looking. You will help the company answer the “why” behind our most stringent risk-prevention efforts, shaping the rationale for prioritizing and mitigating risks across domains. You will serve as a central node connecting technical, governance, and policy perspectives on prioritization, focus and rationale on our approach to frontier risks from AI.

Requirements

• Understand risks from frontier AI systems and have a strong grasp of AI alignment literature.
• Bring deep experience in threat modeling, risk analysis, or adversarial thinking (e.g., security, national security, or safety).
• Know how AI evaluations work and can connect eval results to both capability testing and safeguard sufficiency.
• Enjoy working across technical and policy domains to drive rigorous, multidisciplinary risk assessments.
• Communicate complex risks clearly and compellingly to both technical and non-technical audiences.
• Think in systems and naturally anticipate second-order and cascading risks.

Responsibilities

• Develop and maintain comprehensive threat models across all misuse areas (bio, cyber, attack planning, etc.).
• Develop plausible and convincing threat models across loss of control, self-improvement, and other possible 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 these map to and cover the gambit of severe risks differentially enabled by frontier AI systems.
• Pair closely with Bio and Cyber Leads to size the remaining risk of the designed safeguards and translate threat models into actionable mitigation designs.
• Act as the thought partner and explainer of “why” and “when” for high-investment mitigation efforts—helping stakeholders understand the rationale behind prioritization.
• Serve as the central node connecting technical, governance, and policy perspectives on prioritization, focus and rationale on our approach to misuse risk.

Benefits

• We are an equal opportunity employer, and we do not discriminate on the basis of race, religion, color, national origin, sex, sexual orientation, age, veteran status, disability, genetic information, or other applicable legally protected characteristic.
• Background checks for applicants will be administered in accordance with applicable law, and qualified applicants with arrest or conviction records will be considered for employment consistent with those laws, including the San Francisco Fair Chance Ordinance, the Los Angeles County Fair Chance Ordinance for Employers, and the California Fair Chance Act, for US-based candidates.
• We are committed to providing reasonable accommodations to applicants with disabilities, and requests can be made via this link.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed