Researcher, Alignment Chain of Thought Monitorability
OpenAISan Francisco, CA
AI safety & policy
Full-time
AI safety & policy
Full-time
Routes to impact
Direct high impact on an important cause
Skill-building & building career capital
Description
Research frontier AI monitorability to improve scalable oversight and AI alignment.
- Design experiments on chain-of-thought monitorability and model behavior.
- Build evaluations and monitoring methods for high-stakes AI systems.
- Collaborate across alignment, training, and engineering research teams.
- Publish research that advances AI alignment science.
This text was generated by AI. If you notice any inconsistencies, please let us know using this form.
