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 Teamer
Trajectory LabsBerkeley, CA
Berkeley, CA
Today
Routes to impact
Direct high impact on an important cause
Description
Probe frontier AI systems for vulnerabilities and develop attack strategies to identify and reduce safety failures.
- Design novel attacks and jailbreaks against frontier AI models
- Help build safety and alignment evaluation infrastructure
- Work independently on creative AI red-teaming problems
- Python, agentic coding, and ML security skills are highly valued
This text was generated by AI. If you notice any inconsistencies, please let us know using this form.
Related opportunities
Head of Evaluations, AI Red Teaming
Trajectory LabsBerkeley, CA
Berkeley, CA
1 week ago
AI Cyber Red Teamer
1 week ago
Research Engineer / Research Scientist, Control Red Team
AI Security Institute (AISI)London, UK
London, UK
1 week ago
Research Engineer / Research Scientist, Misuse Red Team
AI Security Institute (AISI)London, UK
London, UK
1 week ago
Research Scientist, Control
Apollo ResearchSan Francisco, CA / London, UK
San Francisco, CA / London, UK
1 week ago
AI Red Team Engineer
Apollo ResearchSan Francisco, CA / London, UK
San Francisco, CA / London, UK
1 week ago
AI Security and Control Researcher
Apollo ResearchLondon, UK / San Francisco, CA
London, UK / San Francisco, CA
1 week ago
Expression of Interest, Technical Roles, Next-Generation Agentic Controls and Forensics
AI Security Institute (AISI)London, UK
London, UK
1 week ago
Join 60k subscribers and sign up for the EA Newsletter, a monthly email with the latest ideas and opportunities