Abuse Investigator, AI Self-Improvement Risk

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

Abuse Investigator, AI Self-Improvement Risk

OpenAISan Francisco, USA

San Francisco, USA

1 month 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