Threat Modeler, Preparedness
Own OpenAI’s holistic approach to identifying, modeling, and forecasting frontier risks from frontier AI systems. Develop threat models across misuse and alignment domains and translate them into actionable mitigation priorities.
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.
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.
Security Engineer, Detection & Response
Lead detection and response engineering efforts, building tooling and processes to monitor threats, investigate incidents, and coordinate responses across Anthropic's technology stack. Requires 5+ years in detection engineering, incident response, or threat hunting.
Security Engineer
Security Engineer responsible for securing AI agent execution, infrastructure, and product surfaces at an applied AI lab building Devin and Windsurf. Requires deep security engineering, software engineering fundamentals, and cloud/web security expertise.
Software Engineer, Security
Security engineer owning cross-cutting auth, authorization, and AI guardrail programs across product and infrastructure. Requires 10+ years shipping security-critical infrastructure and experience with AI/LLM protections.
Principal Infrastructure Security Engineer
Lead security architecture for Crusoe's AI cloud infrastructure, driving zero-trust adoption, workload identity, supply chain security, and hardware-to-software protections at hyperscale. Requires 12+ years infrastructure security experience at a major cloud provider.