AI safety & policy
Full-time
Routes to impact
Direct high impact on an important cause
Description
Conduct research on AI alignment through theoretical and empirical approaches.
- Investigate scalable oversight, learning theory, complexity theory, and related agendas
- Design experiments, develop models, and advance research automation
- Publish papers, talks, and technical writing on research findings
- Collaborate across programs to improve confidence in aligned AI outcomes
This text was generated by AI. If you notice any inconsistencies, please let us know using this form.
