Research Scientist, Post-training Core Model

About the Team

The Post-Training - Core Model team evaluates and improves the capability of the models that power ChatGPT and the OpenAI API.

About the Role

As a Member of Technical Staff on our team, you will research and develop improvements to our models through human data collection, synthetic data studies, supervised fine-tuning, reward modeling, and evaluations.
We’re looking for people who have past scientific experience, are proficient software engineers, and have experience in reinforcement learning or reinforcement learning with human feedback (RLHF) research.

This role is based in San Francisco, CA. We use a hybrid work model of 3 days in the office per week and offer relocation assistance to new employees.

In this role, you will:

• Design, validate, and improve evaluations
• Conduct human data campaigns closely informed by development of new RLHF algorithms
• Conduct and present on machine learning experiments
• Prototype new ideas and algorithms
• Launch your innovations into ChatGPT and the API

You might thrive in this role if you:

• Are a careful scientist and a strong software engineer who wants research with real-world impact
• Aren’t scared of the messiness of handling real-world data
• Can navigate complicated code bases
• Are an effective collaborator and can communicate technical work clearly
• Can iterate quickly on lots of ideas and algorithms
• Love being on the cutting edge of RL and language model research