Interpretability Research Manager — Lead AI Safety

Anthropic Limited; San Francisco (CA); Hybrid; USD 350,000 - 500,000; Full time

Benefits offered by this job

Equity donation matching

Generous vacation and parental leave

Flexible working hours

Job summary

Anthropic Limited in San Francisco is seeking an experienced Research Manager for the Interpretability team to guide a group of researchers and engineers in mechanistic interpretability work. You will set direction, oversee projects, and partner with a research lead to translate ideas into goals and deliverables.

This role requires at least 2-5 years of management of technical teams, a ML/AI background, and strong people skills.

Qualifications

• Experienced manager (2–5+ years) leading highly technical research/engineering teams.
• Background in ML/AI or related technical field.
• Enjoy people management with coaching, performance eval, and hiring for technical roles.
• Strong project management with prioritization and cross-functional collaboration.
• Proven ability to lead teams through ambiguity and change.
• Quick learner capable of discussing complex technical topics and contributing to research.
• Excellent written and verbal communication skills.
• Belief in the transformative potential of advanced AI and a commitment to safe AI.

Responsibilities

• Partner with a research lead on direction, planning, execution, hiring, and people development.
• Set high execution speed and quality, identify process improvements for team effectiveness.
• Coach and support team members to increase impact and career development.
• Drive recruiting efforts, including planning, process improvements, and closing hires.
• Identify opportunities for collaboration with other teams across Anthropic.
• Communicate team updates and results to other teams and leadership.
• Maintain deep understanding of the team's technical work and AI safety implications.

Skills

Management experience

Machine learning background

People management

Project management

Cross-functional coordination

Strong communication

Interest in AI safety

Research leadership

Education

Bachelor's degree

Job description

Anthropic Limited in San Francisco is seeking an experienced Research Manager for the Interpretability team to guide a group of researchers and engineers in mechanistic interpretability work. You will set direction, oversee projects, and partner with a research lead to translate ideas into goals and deliverables.

This role requires at least 2-5 years of management of technical teams, a ML/AI background, and strong people skills.