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, AI Behaviours
White CircleParis, France / London, UK
Paris, France / London, UK
1 month ago
Routes to impact
Direct high impact on an important cause
Skill-building & building career capital
Description
Study how AI agents fail in realistic settings and develop methods to detect unsafe behaviour before deployment.
- Design and run empirical AI safety experiments.
- Build automated audits, evaluations, and benchmarks.
- Investigate misalignment, bias, and agent failures.
- Publish research and improve production safety guardrails.
This text was generated by AI. If you notice any inconsistencies, please let us know using this form.
Related opportunities
Research Engineer, Evals
White CircleParis, France / London, UK
Paris, France / London, UK
1 month ago
Researcher, Alignment Chain of Thought Monitorability
OpenAISan Francisco, CA
San Francisco, CA
3 weeks ago
Machine Learning Engineer
Gray SwanPittsburgh, PA / remote
Pittsburgh, PA / remote
3 weeks ago
Research Scientist, Safety Oversight
Google DeepMindLondon, UK
London, UK
4 weeks ago
Senior Research Scientist, AI Safety Evaluations
FacultyLondon, UK
London, UK
4 weeks ago
Applied AI Data Scientist
AE StudioRemote / US
Remote / US
4 weeks ago
Applied AI Data Scientist
AE StudioFlorianopolis, Brazil / Remote
Florianopolis, Brazil / Remote
4 weeks ago
Software Engineer
FutureSearchRemote
Remote
1 month ago
Join 60k subscribers and sign up for the EA Newsletter, a monthly email with the latest ideas and opportunities