Mechanistic Interpretability Researcher

OpenAI; San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

OpenAI is seeking a researcher passionate about understanding deep networks, with a strong background in engineering and quantitative reasoning. You will develop and carry out a research plan in mechanistic interpretability, collaborating with a motivated team to help ensure future models remain safe as they grow in capability.

You will publish research describing techniques for understanding representations, engineer scalable infrastructure, and guide directions toward measurable usefulness and

Qualifications

• Ph.D. or equivalent research experience in CS/ML.
• 2+ years of research engineering experience with Python or similar languages.
• Interest in mechanistic interpretability and AI safety.

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 scalability.

Skills

Quantitative reasoning

Collaboration

Curiosity

Education

Ph.D. in Computer Science / ML or related field

Tools

Python

Job description

OpenAI is seeking a researcher passionate about understanding deep networks, with a strong background in engineering and quantitative reasoning. You will develop and carry out a research plan in mechanistic interpretability, collaborating with a motivated team to help ensure future models remain safe as they grow in capability.

You will publish research describing techniques for understanding representations, engineer scalable infrastructure, and guide directions toward measurable usefulness and