Research Engineer / Research Scientist, Human Flourishing

The role

This researcher will develop scalable training methods to improve how models understand human values and support agency. You will lead research from open questions to shipped improvements and build RL environments for difficult-to-verify outcomes.

What you will do

• Develop scalable training methods to improve model understanding of human values and agency.
• Lead high-leverage research from open questions to shipped improvements.
• Build RL environments for difficult-to-verify outcomes.
• Create evaluations grounded in human expertise and feedback.
• Test whether measures of model behavior predict better long-term outcomes.
• Build new 0 to 1 capabilities in human domains.
• Partner with product, engineering, and domain expert teams to deploy methods.
• Assess AI impacts on human flourishing at scale.

Required qualifications

• Strong research record in pretraining or RL / post-training research, especially in a hard-to-verify area.
• Hands-on builder who can turn ideas into rigorous experiments.
• Ability to write and debug code.
• Ability to work directly with data and training infrastructure.

Nice to have

• Strong LLM research skills combined with deep expertise in education, mental health, or a related field of human benefit.

About the company

OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity. They seek to safely deploy AI to the world through their products.