The Effective Altruism
Opportunities Board
Work on the world's most pressing problems. Browse jobs, fellowships, internships, courses, and more at high-impact organisations.
Research Scientist, Applied White-Box Methods
FAR.AIBerkeley, CA
Berkeley, CA
Today
Salary
$150,000
Routes to impact
Direct high impact on an important cause
Description
Research scientist developing and evaluating white-box methods that use model internals to improve AI system safety.
- Stress-test interpretability methods on realistic agentic coding and long-context tasks
- Own and accelerate the team's research agenda, propose new directions
- Publish findings, engage with the alignment community, attend conferences
- Access shared compute cluster and dedicated infrastructure team
This text was generated by AI. If you notice any inconsistencies, please let us know using this form.
Related opportunities
Machine Learning Research Scientist
AI X-risk Institute (AIXI Labs)London, UK / Berkeley, CA
London, UK / Berkeley, CA
2 weeks ago
Member of Technical Staff, Engineering
AI DigestRemote
Remote
4 weeks ago
Red Team Specialist, Cyber
OpenAISan Francisco, CA / Seattle, WA / Washington, DC
San Francisco, CA / Seattle, WA / Washington, DC
4 weeks ago
Research Scientist, Manipulation Evaluations
Apart ResearchRemote (Europe preferred)
Remote (Europe preferred)
3 months ago
Research Engineer, Scalable Interpretability
TransluceSan Francisco, CA
San Francisco, CA
3 months ago
Technical Associate, Robotics and Physical AI
Cambridge, MA
3 weeks ago
Research Lead, Pre-Training Safety
FAR.AIRemote / Berkeley, CA / Singapore
Remote / Berkeley, CA / Singapore
2 weeks ago
Data Scientist
Innovations for Poverty ActionKenya / Ghana / Colombia / Peru
Kenya / Ghana / Colombia / Peru
2 months ago
Join 60k subscribers and sign up for the EA Newsletter, a monthly email with the latest ideas and opportunities