Researcher, Misalignment Research | EA Opportunities Board

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

Researcher, Misalignment Research

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

Increasing awareness of institutional decision making challenges in AI safety

Description

A senior researcher role at OpenAI for an experienced AI safety professional focused on identifying and stress-testing misalignment risks in frontier AGI systems.

Focus area - design worst-case demonstrations and adversarial evaluations targeting deceptive behavior, scheming, reward hacking, and power-seeking in AI systems
Scope - build automated red-teaming infrastructure and conduct research on alignment failure modes, with findings directly shaping product launches and safety strategy
Collaboration - partner across research, engineering, policy, and legal teams; publish internal and external papers to advance industry-wide safety practice
Compensation - $295K–$445K + equity, based in San Francisco

Apply directly at openai.com/careers

This text was generated by AI. If you notice any inconsistencies, please let us know using this form

View opportunity

Related opportunities