AI safety & policy
Full-time
Salary
$200,000-$300,000
Routes to impact
Direct high impact on an important cause
Description
Identify and run AI safety research projects, especially on rogue agent detection, ML experiments, and technical analysis.
- Identify promising alignment research directions with action-relevant insights
- Design, triage, and run ML experiments across changing projects
- Analyze data and transcripts to uncover important patterns and leads
- Write internal research updates and public-facing blog posts, websites, and papers
This text was generated by AI. If you notice any inconsistencies, please let us know using this form.



