The Effective Altruism
Opportunities Board
Work on the world's most pressing problems. Browse jobs, fellowships, internships, courses, and more at high-impact organisations.
Red Team Specialist, Cyber
OpenAISan Francisco, CA / Seattle, WA / Washington, DC
San Francisco, CA / Seattle, WA / Washington, DC
1 week ago
Routes to impact
Direct high impact on an important cause
Description
Evaluate AI systems for cyber capabilities, safeguards, and real-world abuse risks through rigorous red-team testing and automated evaluation.
- Design cyber capability and safeguard evaluations across models and products
- Build testing infrastructure, harnesses, and reproducible adversarial experiments
- Assess attacker uplift, vulnerabilities, and novel agentic abuse risks
- Translate findings into risk assessments and mitigation recommendations
This text was generated by AI. If you notice any inconsistencies, please let us know using this form.
Related opportunities
Research Scientist, Control
Apollo ResearchSan Francisco, CA / London, UK
San Francisco, CA / London, UK
1 day ago
AI Red Team Engineer
Apollo ResearchSan Francisco, CA / London, UK
San Francisco, CA / London, UK
1 day ago
AI Security and Control Researcher
Apollo ResearchLondon, UK / San Francisco, CA
London, UK / San Francisco, CA
1 day ago
Security Research Engineer
AI Verification and Evaluation Research Institute (AVERI)Remote / US / Mexico / Canada
Remote / US / Mexico / Canada
3 days ago
Head of Evaluations, AI Red Teaming
Trajectory LabsBerkeley, CA
Berkeley, CA
3 days ago
AI Security Researcher
Apollo ResearchLondon, UK / San Francisco, CA
London, UK / San Francisco, CA
3 days ago
Member of Technical Staff, Embedded Assessments
Model Evaluation & Threat Research (METR)Berkeley, CA
Berkeley, CA
1 week ago
Member of Technical Staff, Cyberforensics
Model Evaluation & Threat Research (METR)Berkeley, CA
Berkeley, CA
1 week ago
Join 60k subscribers and sign up for the EA Newsletter, a monthly email with the latest ideas and opportunities