[Expression of Interest] Research Manager, Interpretability
Core
Manage a team of expert researchers and engineers focused on reverse-engineering neural networks to ensure AI safety through mechanistic interpretability.
Role type
Senior manager for AI safety research (mechanistic interpretability)
Builds
Mechanistic understanding of large language models and neural network parameters
Domain
AI safety / Machine Learning / Neural Networks
Deliverable
research
Required skills
People management, coaching and mentorship, performance evaluation, hiring for technical roles, project management, cross-functional collaboration, technical literacy in ML/AI
Preferred skills
Scaling engineering infrastructure, managing open-ended exploratory research agendas, familiarity with mechanistic interpretability
Responsibilities
Partner with research lead on direction and execution, set execution standards and improve processes, coach team members on career development, drive recruiting efforts, facilitate cross-team collaboration, communicate results to leadership
Seniority
Senior, hands-on IC manager
