The Effective Altruism
Opportunities Board
Work on the world's most pressing problems. Browse jobs, fellowships, internships, courses, and more at high-impact organisations.
Researcher, Alignment Chain of Thought Monitorability
OpenAISan Francisco, CA
San Francisco, CA
Today
Routes to impact
Direct high impact on an important cause
Skill-building & building career capital
Description
Conduct empirical research on AI model monitorability to improve scalable oversight and alignment methods.
- Design experiments on chain-of-thought monitorability.
- Build evaluations for detecting high-stakes model misbehavior.
- Study how training methods affect monitorability.
- Collaborate to improve practical AI oversight and safety.
This text was generated by AI. If you notice any inconsistencies, please let us know using this form.
Related opportunities
Researcher, Alignment Training
OpenAISan Francisco, USA
San Francisco, USA
1 month ago
Member of Technical Staff, Research
Model Evaluation & Threat Research (METR)Berkeley, CA
Berkeley, CA
4 days ago
Senior Machine Learning Data Platform Developer
LawZeroMontreal, Canada
Montreal, Canada
1 week ago
ML Engineer
Tilde ResearchSan Francisco, CA
San Francisco, CA
1 week ago
ML Researcher
Tilde ResearchSan Francisco, CA
San Francisco, CA
1 week ago
Hardware / Kernel Engineer
Tilde ResearchSan Francisco, CA
San Francisco, CA
1 week ago
Product Engineer
GoodfireSan Francisco, CA
San Francisco, CA
1 week ago
Research Engineer
PrincipiaLondon, UK
London, UK
1 week ago
Join 60k subscribers and sign up for the EA Newsletter, a monthly email with the latest ideas and opportunities