Researcher, Frontier Robustness
OpenAISan Francisco, CA
AI safety & policy
Information security
Full-time
AI safety & policy
Information security
Full-time
Salary
$295K – $500K
Routes to impact
Direct high impact on an important cause
Description
Research and test methods to secure frontier AI systems, from threat modeling and experiments to practical defenses and monitoring.
- Run experiments with frontier models to uncover failure modes in sandboxes and research infrastructure
- Develop adversarial tests for sandbox escapes, unauthorized communication, and access to sensitive systems
- Prototype and evaluate defenses that strengthen isolation and limit the impact of compromised boundaries
- Build and red-team safeguards and monitors of model reasoning and actions
- Create automated evaluations to track security as models, environments, and attacks change
This text was generated by AI. If you notice any inconsistencies, please let us know using this form.



