Research Manager, Interpretability

Details

Anthropic is seeking expressions of interest for a Research Manager on its Interpretability team. There are no open Research Manager positions on the Interpretability team at this time, but the team is actively growing its Research Engineer and Research Scientist groups and welcomes applicants who are open to individual contributor roles.

Anthropic's Interpretability team works on mechanistic interpretability: reverse engineering how trained neural networks work, discovering how model parameters map to meaningful algorithms, and developing methods to make advanced AI systems safer. The team's research includes superposition, monosemanticity, dictionary learning, feature-based circuits, attribution graphs, multi-hop reasoning, planning, and chain-of-thought faithfulness in large language models.

Responsibilities

• Partner with a research lead on direction, project planning and execution, hiring, and people development.
• Set and maintain a high bar for execution speed and quality, including improving processes that help the team operate effectively.
• Coach and support team members to increase their impact and develop their careers.
• Drive recruiting efforts, including hiring planning, process improvements, sourcing, and closing.
• Identify and support collaboration opportunities with other Anthropic teams.
• Communicate team updates and results to teams and leadership.
• Maintain a deep understanding of the team's technical work and its implications for AI safety.
• Manage team execution, careers, performance, cross-team relationships, and the hiring pipeline.

Requirements

• 2–5 years of experience as a manager, with a track record of leading highly technical research and/or engineering teams.
• Background in machine learning, artificial intelligence, or a related technical field.
• Experience with people management, coaching and mentorship, performance evaluation, career development, and hiring for technical roles.
• Strong project management skills, including prioritization and cross-functional coordination and collaboration.
• Experience managing technical teams through ambiguity and change.
• Ability to quickly learn and contribute to discussions on complex technical topics.
• Strong written and verbal communication skills.
• Passion for helping ensure that the development of advanced AI systems has a positive impact.
• Bachelor's degree or an equivalent combination of education, training, and experience.
• A relevant field of study demonstrated through coursework, training, or professional experience.

Preferred Qualifications

• Experience scaling engineering infrastructure.
• Experience working on open-ended, exploratory research agendas aimed at foundational insights.
• Familiarity with Anthropic's work and mechanistic interpretability.

Work Arrangement

The role is expected to be based in Anthropic's San Francisco office three days per week. Anthropic currently expects all staff to work from one of its offices at least 25% of the time.

Benefits

Anthropic offers competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and an office space for collaboration. Anthropic sponsors visas and makes reasonable efforts to obtain a visa for candidates who receive an offer, with support from an immigration lawyer.