Software Engineer, Post-Training Research
OpenAI · San Francisco
About the Team Post-Training is responsible for training the models to be deployed into ChatGPT, the API, and future products. The team partners closely with research and product teams across the company, and conducts research as a final step to prepare for real world deployment to millions of users, ensuring that our models are safe, efficient, and reliable. About the Role We are looking for a seasoned engineer who can help us with a variety of engineering challenges. Some example projects in this role: - Rapidly prototype and develop internal products or tools used by researchers, such as visualization for our evaluation of models. - Refactor a large code base for cleaner module designs. - Redesign experiment configuration and evaluation systems. Ideal candidates - Navigate large code bases independently and quickly - Can debug through complex systems - Can navigate high energy environments with fast changing priorities - Are comfortable being scrappy and working independently at fast speeds 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: - Rapidly prototype and build tooling or visualization for researchers. - Collaborate with research teams. - Design, implement, test, and debug code across our stack. You might thrive in this role if you: - Strong background in writing maintainable, testable, clean code. - Enjoyment of code quality, refactoring, and building robust internal codebases. - Are a T-shaped engineer, with a broad range of experiences, but also an expert in one area. We are not terribly opinionated on a particular area, but examples could be expert level familiarity with the Python language, or expert experience building tools, or exceptional debugger. - Fast learner; you will need to understand how post training works on a high level and pick up different aspects of research needs. - Have ex