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 Cyber Red Teamer
Today
Routes to impact
Direct high impact on an important cause
Description
Test frontier AI models against cyber safeguards, identifying failures that can improve safety evaluations, training, and deployment decisions.
- Design novel jailbreak and attack strategies against model guardrails
- Document vulnerabilities involving exploits, privilege escalation, and intrusion assistance
- Apply offensive security thinking to emerging AI attack surfaces
This text was generated by AI. If you notice any inconsistencies, please let us know using this form.
Related opportunities
Member of Technical Staff, Embedded Assessments
Model Evaluation & Threat Research (METR)Berkeley, CA
Berkeley, CA
Yesterday
Research Engineer - AI Verification
Singapore AI Safety Hub (SASH)Remote / London, UK / San Francisco, CA / Singapore
Remote / London, UK / San Francisco, CA / Singapore
1 week ago
Member of Technical Staff, Secure Intelligence Institute
PerplexitySan Francisco, CA
San Francisco, CA
1 week ago
Expression of Interest, Cyber and Autonomous Systems Team
AI Security Institute (AISI)London, UK
London, UK
3 weeks ago
AI Security and Control Engineer
Apollo ResearchLondon, UK / San Francisco, USA
London, UK / San Francisco, USA
2 months ago
Software Engineer - Core Technology
AI Security Institute (AISI)London, UK
London, UK
2 months ago
Machine Learning Engineer
10a LabsRemote (US)
Remote (US)
2 months ago
AI Red Teamer, Cyber
10a LabsRemote (US)
Remote (US)
2 months ago
Join 60k subscribers and sign up for the EA Newsletter, a monthly email with the latest ideas and opportunities