The Effective Altruism
Opportunities Board
Work on the world's most pressing problems. Browse jobs, fellowships, internships, courses, and more at high-impact organisations.
AI Red Team Analyst
AlignerrRemote
Remote
4 months ago
Routes to impact
Skill-building & building career capital
Direct high impact on an important cause
Testing your fit for a certain career path
Description
Help stress-test AI systems by uncovering vulnerabilities and evaluating model safety under adversarial conditions.
- Design red-team exercises and jailbreak attempts
- Evaluate outputs for safety, bias, and policy violations
- Document exploits and recommend mitigations
- Refine AI security testing protocols and evaluation rubrics
This text was generated by AI. If you notice any inconsistencies, please let us know using this form.
Related opportunities
AI / Emerging Technology Security Analyst
AlignerrRemote
Remote
4 months ago
Research Fellow
10a LabsRemote (US)
Remote (US)
4 months ago
AI Security Research Engineer
0LabsRemote
Remote
5 months ago
Data Centre Security Architect
Lucid ComputingSan Francisco, CA / London, UK
San Francisco, CA / London, UK
3 weeks ago
Member of Technical Staff, Embedded Assessments
Model Evaluation & Threat Research (METR)Berkeley, CA
Berkeley, CA
1 month ago
Content Editor
Remote
2 months ago
Senior Advisor, Contingency Planning, Loss of Control
Remote
2 weeks ago
Safeguards Enforcement Analyst, Bio Harms
AnthropicRemote / San Francisco, CA / New York City, NY/ Washington, DC
Remote / San Francisco, CA / New York City, NY/ Washington, DC
2 months ago
Join 60k subscribers and sign up for the EA Newsletter, a monthly email with the latest ideas and opportunities