Mechanistic Interpretability Researcher

OpenAI; California (MO); On-site; USD 180,000 - 320,000; Full time

Job summary

OpenAI is seeking a researcher passionate about understanding deep networks, with a strong background in engineering, quantitative reasoning, and the research process. You will develop and carry out a research plan in mechanistic interpretability, in close collaboration with a highly motivated team.

You will help ensure future models remain safe as they grow, and you will play a critical role in OpenAI's mission to build and deploy safe AGI.

Qualifications

• Ph.D. or equivalent research experience in computer science or ML.
• Strong background in engineering, quantitative reasoning, and the research process.
• 2+ years of research engineering experience.
• Proficiency in Python or similar languages.

Responsibilities

• Develop and publish research on techniques for understanding representations of deep networks.
• Engineer infrastructure for studying model internals at scale.
• Collaborate across teams on projects aligned with OpenAI's goals.
• Guide research directions toward demonstrable usefulness and long-term scalability.

Skills

Python

Education

Ph.D. or equivalent research experience in CS/ML

Job description

OpenAI is seeking a researcher passionate about understanding deep networks, with a strong background in engineering, quantitative reasoning, and the research process. You will develop and carry out a research plan in mechanistic interpretability, in close collaboration with a highly motivated team.

You will help ensure future models remain safe as they grow, and you will play a critical role in OpenAI's mission to build and deploy safe AGI.