AI safety & policy
Full-time
Salary
$380K – $500K
Routes to impact
Direct high impact on an important cause
Description
Lead research on evaluating and improving misalignment monitoring for frontier AI systems.
- Set technical direction for monitoring research and safety evaluation priorities
- Design rigorous evaluations to measure monitor effectiveness and identify failure modes
- Stress-test and red-team monitors to find behaviors that evade detection
- Investigate false positives and missed detections to improve monitoring accuracy
- Build scalable evaluation tools and translate findings into safety system improvements
This text was generated by AI. If you notice any inconsistencies, please let us know using this form.



