Research Engineer / Scientist, Model Behavior

OpenAI is seeking a Research Engineer / Scientist for the Model Behavior team within their Alignment division. This role focuses on defining core model behaviors using alignment methods like RLHF/RLAIF to reflect fundamental values and improve creative intelligence. The successful candidate will develop challenging evaluations, novel methods to train models, and work on creating the next generation of human-AI interfaces.

Key responsibilities include:

• Designing challenging evaluations related to creative intelligence
• Developing scalable synthetic data techniques
• Training models and running experiments to study data quality
• Iterating on research experiments and communicating insights
• Integrating core model behaviors into models powering ChatGPT
• Collaborating with product, design, and engineering teams

The ideal candidate should have:

• Strong technical background and familiarity with the LLM stack
• Experience in applied Machine Learning
• Proficiency in Python
• Ability to lead ambitious projects with clear communication
• Experience with designing research experiments and evaluations
• Knowledge of Machine Learning, Deep Learning, and Large Language Models
• Familiarity with frontend technologies (React/TypeScript/JS)

Additional beneficial skills include experience with large-scale data systems, design engineering, and working on novel interfaces.

This role is based in San Francisco, CA, with a hybrid work model of 3 days in the office per week. OpenAI offers relocation assistance and is committed to diversity, equal opportunity, and providing reasonable accommodations to applicants with disabilities.

Join OpenAI in shaping the future of AI technology and ensuring its benefits are widely shared.