Research Engineer / Scientist, Interpretability

Overview

Researcher focused on understanding deep networks and ensuring AI safety.

Ideal candidate has a strong background in AI safety and mechanistic interpretability with 2+ years of experience.

Locations

• United States, California, San Francisco

Requirements

• Ph.D. or research experience in computer science or related field
• 2+ years of research engineering experience
• Proficiency in Python or similar languages

Responsibilities

• Develop and publish research on deep network representations
• Engineer infrastructure for model internals
• Collaborate on unique projects
• Guide research directions for scalability

Benefits

• Medical, dental, and vision insurance
• Mental health support
• 401(k) with 50% matching
• Generous time off
• Paid parental leave
• Annual learning stipend