Mechanistic Interpretability Researcher for Safe AI

Seoulstart; San Francisco (CA); On-site; USD 180,000 - 250,000; Full time

Job summary

OpenAI is seeking a researcher focused on understanding deep networks, with strong engineering and quantitative reasoning skills, to develop and execute a plan in mechanistic interpretability. This role involves building infrastructure to study model internals at scale, publishing findings, and collaborating across teams to advance safe AGI initiatives.

The position emphasizes rigorous research processes and collaboration to influence future models while maintaining safety considerations in

Qualifications

• Develop and publish research on techniques for understanding representations of deep networks.
• Engineer infrastructure for studying model internals at scale.
• Collaborate across teams to work on projects that OpenAI is uniquely suited to pursue.

Responsibilities

• Develop and publish research on techniques for understanding representations of deep networks.
• Engineer infrastructure for studying model internals at scale.
• Collaborate across teams to work on projects that OpenAI is uniquely suited to pursue.

Job description

OpenAI is seeking a researcher focused on understanding deep networks, with strong engineering and quantitative reasoning skills, to develop and execute a plan in mechanistic interpretability. This role involves building infrastructure to study model internals at scale, publishing findings, and collaborating across teams to advance safe AGI initiatives.

The position emphasizes rigorous research processes and collaboration to influence future models while maintaining safety considerations in