AI safety & policy
Information security
Full-time
Routes to impact
Direct high impact on an important cause
Description
Lead the development of cyber safety capabilities for frontier AI systems, spanning adversarial evaluation, defenses, infrastructure, and technical risk assessment.
- Design offensive cyber evaluations, benchmarks, guardrails, and automated detection systems
- Develop catastrophic cyber harm taxonomies and evolving evaluation frameworks
- Build and mentor a cybersecurity team and establish technical standards
- Advise AI labs and other partners on security risks and mitigations
This text was generated by AI. If you notice any inconsistencies, please let us know using this form.



