Researcher, Alignment Science | 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, Alignment Science

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 research role at OpenAI for experienced ML researchers focused on building scalable alignment methods that ensure frontier AI models follow human intent, remain honest, and behave safely.

Focus area - design and run experiments on intent following, honesty, calibration, and robustness using reinforcement learning and empirical ML methods
Impact - work translates directly into deployed models, with results eligible for external publication when they advance the broader science of alignment
Compensation - $250K–$445K base salary plus equity; hybrid model (3 days in office) based in San Francisco, with relocation assistance available
Ideal background - hands-on LLM training and evaluation experience, strong Python and PyTorch skills, and comfort with RL, post-training, or scalable oversight research

Apply directly via the OpenAI careers page.

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

View opportunity

Related opportunities

Researcher, Alignment Training

OpenAISan Francisco, USA

San Francisco, USA

1 month ago