Mechanistic Interpretability Researcher for AI Safety

OpenAI; Los Angeles (CA); On-site; USD 120,000 - 150,000; Full time

Job summary

A leading AI research company in California is seeking a passionate Researcher in Mechanistic Interpretability. You will develop techniques for understanding deep learning models. The role requires a Ph.D. or equivalent experience in related fields and 2+ years in research engineering. Collaborating in a curiosity-driven team, you will impact AI safety's trajectory as models grow in capability. This position embraces the core values of safety and human benefit in AI deployment, contributing to building a better future.

Qualifications

• 2+ years of research engineering experience.
• Experience in AI safety or mechanistic interpretability.
• Enthusiasm for long-term AI safety and its technical paths.

Responsibilities

• Develop and publish research on techniques for understanding representations of deep networks.
• Engineer infrastructure for studying model internals at scale.
• Collaborate on projects that OpenAI is uniquely suited to pursue.
• Guide research directions toward demonstrable usefulness.

Skills

Python or similar languages

Quantitative reasoning

Research engineering experience

Deep learning understanding

AI safety knowledge

Education

Ph.D. in computer science, machine learning, or related field

Job description

A leading AI research company in California is seeking a passionate Researcher in Mechanistic Interpretability. You will develop techniques for understanding deep learning models. The role requires a Ph.D. or equivalent experience in related fields and 2+ years in research engineering. Collaborating in a curiosity-driven team, you will impact AI safety's trajectory as models grow in capability. This position embraces the core values of safety and human benefit in AI deployment, contributing to building a better future.