About the role
About the Team
The Post Training team is responsible for training and improving pre-trained models to be deployed into ChatGPT, the API, and potential future products. In the Model Experience team, we shape the default character and behavior of ChatGPT: how the model communicates, responds to users, uses its capabilities, and behaves across different contexts and languages. Our goal is to make every interaction with ChatGPT thoughtful, helpful, and trustworthy. We take an opinionated view of what good human–AI interaction should look like, then turn that vision into real model behavior through human data, evaluations, reward models, and post-training.
Our work sits at the intersection of research, product, and model design. We partner closely with teams across OpenAI to conduct research and ensure our models are thoughtful, safe, reliable to serve millions of users.
About the Role
As a Research Engineer / Scientist, you will research and develop improvements to our models. Our team works in research areas combining reinforcement learning and products.
We're looking for individuals with strong ML engineering skills and research experience, especially with novel and highly capable models. An ideal candidate is passionate about product-driven research and the quality of human-AI interaction.
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
- Own and pursue a research agenda to improve model capability and performance.
- Collaborate closely with the other research and product teams, allowing customers to optimize their own models.
- Build robust evaluations for tracking modeling improvements.
- Design, implement, test, and debug code across our research stack.
You might thrive in this role if you
- Have a deep understanding of machine learning and machine learning applications.
- Have good judgment about model behavior and can communicate this judgment effectively.
- Enjoy taking ambitious, qualitative problems and turning them into concrete training interventions.
- Have a working knowledge of relevant models, and building evaluations for model capability improvement.
- Are comfortable diving into a large ML codebase to debug.
- Thrive in a dynamic, technically complex, and collaborative environment.