Research Engineer / Scientist, Interpretability

OpenAI is seeking a Research Engineer/Scientist to join their Interpretability team. The team studies internal representations of deep learning models and is interested in applying their understanding to ensure the safety of powerful AI systems. The role involves developing and publishing research on techniques for understanding representations of deep networks, engineering infrastructure for studying model internals at scale, and collaborating across teams to work on projects.

Requirements

• Ph.D. or research experience in computer science, machine learning, or a related field
• 2+ years of research engineering experience and proficiency in Python or similar languages
• Experience in AI safety, mechanistic interpretability, or spiritually related disciplines