[Expression of Interest] Research Manager, Interpretability

Highlights

• Reverse-engineer how large language models work internally for AI safety.
• Lead research on superposition and decomposing models into interpretable features.
• Translate cutting-edge interpretability ideas into tangible safety research goals.

What they offer

• Competitive compensation and benefits
• Optional equity donation matching
• Generous vacation and parental leave
• Flexible working hours
• Office space in San Francisco for collaboration

Ideal candidate

An experienced technical manager with ML background who loves coaching researchers and thrives in ambiguity, passionate about making transformative AI safe through mechanistic understanding.

Requirements

• Minimum 2-5 years experience effectively leading highly technical research and/or engineering teams
• Background in machine learning, AI, or related technical field
• Experience with coaching, mentorship, performance evaluation, career development and hiring for technical roles
• Strong project management skills including prioritization and cross-functional coordination
• Experience managing technical teams through ambiguity and change
• Ability to understand and contribute to complex technical topics
• Strong written and verbal communication skills
• Bachelor's degree or equivalent combination of education, training and experience