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 Engineer / Research Scientist, Misuse Red Team
AI Security Institute (AISI)London, UK
London, UK
Today
Deadline
2026-09-30
Routes to impact
Direct high impact on an important cause
Description
Research frontier AI misuse risks by developing attacks, evaluating safeguards, and strengthening protections against dangerous model capabilities.
- Design automated attacks and evaluations for frontier AI safeguards.
- Investigate data poisoning, monitoring, jailbreaks, and other attack vectors.
- Produce findings that inform AI developers and government decision-making.
- Work across research science and research engineering.
This text was generated by AI. If you notice any inconsistencies, please let us know using this form.
Related opportunities
Research Engineer / Research Scientist, Control Red Team
AI Security Institute (AISI)London, UK
London, UK
Today
Research Scientist, Control
Apollo ResearchSan Francisco, CA / London, UK
San Francisco, CA / London, UK
Yesterday
Head of Evaluations, AI Red Teaming
Trajectory LabsBerkeley, CA
Berkeley, CA
2 days ago
Red Team Specialist, Cyber
OpenAISan Francisco, CA / Seattle, WA / Washington, DC
San Francisco, CA / Seattle, WA / Washington, DC
1 week ago
Machine Learning Engineer
10a LabsRemote (US)
Remote (US)
2 months ago
Machine Learning Researcher
Gray SwanRemote
Remote
3 months ago
AI Security Research Engineer
0LabsRemote
Remote
4 months ago
Expression of Interest, Technical Roles, Next-Generation Agentic Controls and Forensics
AI Security Institute (AISI)London, UK
London, UK
2 days ago
Join 60k subscribers and sign up for the EA Newsletter, a monthly email with the latest ideas and opportunities