Researcher, Alignment Training | 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 Training

OpenAISan Francisco, USA

San Francisco, USA

1 month ago

AI safety & policy

Full-time

Salary

$250K – $445K

Routes to impact

Direct high impact on an important cause

Skill-building & building career capital

Description

OpenAI is seeking a senior researcher to join its Alignment Training team in San Francisco, focused on shaping how frontier models develop durable, aligned behavioral tendencies across the training stack.

Research focus - Study how pre-training, mid-training, and post-training choices shape model behavior, including instruction-following, honesty, and reliability under new conditions.
Data and evaluation - Develop synthetic data methods and build evaluation loops that connect model behavior back to training objectives for faster, clearer iteration.
Collaboration - Work across pre-training, post-training, alignment, and product-facing teams to translate research insights into better deployed systems.
Compensation - $250K–$445K base salary plus equity, based in San Francisco.

Apply directly through OpenAI's careers portal at the link above.

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

View opportunity

Related opportunities