Research Engineer / Research Scientist - Personal AGI, Personality and Model Behavior

OpenAI•San Francisco, CA

3d•$295,000 - $555,000•Hybrid

About The Position

The Personality & Model Behavior team, within OpenAI’s broader Personal AGI team conducts research on how to shape personalities and guide the behavior of models. We think about topics such as emotional intelligence, reasoning, and how models interact thoughtfully with users. We’re particularly interested in understanding how individual users want ChatGPT to behave, and creating personalized models that feel uniquely tailored to each user. We integrate this research into ChatGPT and other OpenAI products that are used by hundreds of millions of users. We're looking for individuals with strong ML engineering skills and research experience, especially with novel and highly capable models, and in areas like reinforcement learning and reward modeling. An ideal candidate is passionate about product-driven research. In this role, you will: Conduct research around personalization, personality, and model behavior by leveraging and developing tools such as synthetic data, reward modeling, and reinforcement learning. Build robust evaluations and model training pipelines to facilitate our research. Innovate new post-training methods. 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.

Requirements

Strong ML engineering skills and research experience, especially with novel and highly capable models, and in areas like reinforcement learning and reward modeling.
Passionate about product-driven research.
Deep understanding of machine learning and its applications.
Prior knowledge in training and optimizing models and building evaluations.
Willing to dive into large ML codebases to debug issues.
Thrive in dynamic and technically complex environments.
Track record of delivering innovative, out-of-the-box solutions to address real-world constraints.

Responsibilities

Conduct research around personalization, personality, and model behavior by leveraging and developing tools such as synthetic data, reward modeling, and reinforcement learning.
Build robust evaluations and model training pipelines to facilitate our research.
Innovate new post-training methods.