AI safety & policy
Full-time
Salary
$207K – $335K
Routes to impact
Direct high impact on an important cause
Skill-building & building career capital
Description
Shape behavioral safety policy for frontier AI systems by translating alignment risks into safeguards, evaluations, and monitoring.
- Investigate model misalignment across long-horizon agent behavior.
- Develop policies, threat models, evaluations, and safety safeguards.
- Partner with research, engineering, security, and product teams.
- Inform deployment decisions and post-deployment monitoring.
This text was generated by AI. If you notice any inconsistencies, please let us know using this form.
