The Effective Altruism
Opportunities Board
Work on the world's most pressing problems. Browse jobs, fellowships, internships, courses, and more at high-impact organisations.
Expression of Interest, Red Team
AI Safety Ideas (AISI)London, UK
London, UK
Today
Routes to impact
Direct high impact on an important cause
Skill-building & building career capital
Testing your fit for a certain career path
Description
Join a government AI red teaming group researching and stress testing frontier AI system failures, misuse risks and control weaknesses.
- Research alignment failures and deceptive model behaviour
- Develop adversarial evaluations and attack tooling
- Collaborate with frontier labs and government stakeholders
- Influence AI deployment, governance and safety decisions
This text was generated by AI. If you notice any inconsistencies, please let us know using this form.
Related opportunities
Researcher, Misalignment Research
OpenAISan Francisco, USA
San Francisco, USA
4 weeks ago
Senior Software Engineer, Chem-Bio
AI Security Institute (AISI)London, United Kingdom
London, United Kingdom
4 weeks ago
Senior Software Engineer, Chem-Bio
AI Security Institute (AISI)London, United Kingdom
London, United Kingdom
4 weeks ago
Research Engineer / Research Scientist, Model Transparency
AI Safety Ideas (AISI)London, UK
London, UK
2 days ago
Member of Technical Staff, Security / Engineering / Research
Security Level 5Bay Area, USA
Bay Area, USA
Today
Machine Learning Researcher
Gray SwanRemote
Remote
1 week ago
Security Preparedness Lead, Coding Agents
OpenAISan Francisco, CA
San Francisco, CA
1 week ago
PhD Fellowship, Mechanistic Interpretability for Large Language Model Security
University of CopenhagenCopenhagen, Denmark
Copenhagen, Denmark
2 weeks ago
Join 60k subscribers and sign up for the EA Newsletter, a monthly email with the latest ideas and opportunities