The Effective Altruism

Opportunities Board

Work on the world's most pressing problems. Browse jobs, fellowships, internships, courses, and more at high-impact organisations.
Add opportunity
Get notified
Add opportunity
Get notified about new roles
                Give us feedback →
                Abuse Investigator, AI Self-Improvement Risk
                Abuse Investigator, AI Self-Improvement Risk
                OpenAISan Francisco, USA
                AI safety & policy
                Full-time
                4 weeks ago
                San Francisco, USA
                4 weeks ago
                AI safety & policy
                Full-time
                Routes to impact
                Direct high impact on an important cause
                Skill-building & building career capital
                Description
                A San Francisco-based role on OpenAI's Intelligence & Investigations team, focused on identifying and investigating autonomous or agentic AI behaviors that may introduce safety risks.
                • Investigate model behaviors such as multi-step planning, capability chaining, tool use, persistence, and workaround patterns that fall outside intended safeguards
                • Develop proactive signals and tracking strategies to surface emerging agentic risk patterns across OpenAI's platform
                • Identify gaps in existing safety evaluations and monitoring systems, and propose improvements
                • Communicate findings clearly to technical, policy, and leadership stakeholders; 6+ years of investigation or threat analysis experience required
                Compensation: $288K–$320K + equity. Apply directly here.
                No visa sponsorship information was listed for this role.
                This text was generated by AI. If you notice any inconsistencies, please let us know using this form
                View opportunity
                Related opportunities
                Member of Technical Staff
                Member of Technical Staff
                CivAIBerkeley, USA
                AI safety & policy
                Institutional decision-making
                Full-time
                1 week ago
                Berkeley, USA
                1 week ago
                Researcher, Misalignment Research
                Researcher, Misalignment Research
                OpenAISan Francisco, USA
                AI safety & policy
                Full-time
                2 weeks ago
                San Francisco, USA
                2 weeks ago
                Product Manager, Cyber Safety
                Product Manager, Cyber Safety
                OpenAISan Francisco, USA
                Information security
                AI safety & policy
                Full-time
                2 weeks ago
                San Francisco, USA
                2 weeks ago
                Policy Analyst, Economic and Societal Transformation
                Policy Analyst, Economic and Societal Transformation
                Americans for Responsible InnovationWashington, USA
                AI safety & policy
                Full-time
                1 week ago
                Washington, USA
                1 week ago
                Research Analyst / Senior Research Analyst
                Research Analyst / Senior Research Analyst
                Forecasting Research Institute (FRI)Remote
                Global priorities research
                AI safety & policy
                Full-time
                1 week ago
                Remote
                1 week ago
                AI Policy Fellow, California Department of Technology
                AI Policy Fellow, California Department of Technology
                California Council on Science & Technology (CCST)Remote (California, USA)
                AI safety & policy
                Institutional decision-making
                Full-time
                Fellowship
                1 week ago
                Remote (California, USA)
                1 week ago
                Applied Control Researcher
                Applied Control Researcher
                Apollo ResearchLondon, United Kingdom / San Francisco, USA
                AI safety & policy
                Full-time
                2 weeks ago
                London, United Kingdom / San Francisco, USA
                2 weeks ago
                Head of Policy Analysis
                Head of Policy Analysis
                Centre pour la Sécurité de l'IA (CeSIA)Remote (Europe)
                AI safety & policy
                Full-time
                Deadline soon
                2 weeks ago
                Remote (Europe)
                2 weeks ago
                Join 60k subscribers and sign up for the EA Newsletter, a monthly email with the latest ideas and opportunities