Interpretability Team Manager, Anthropic

• Thus, we are looking for Team Managers to help cover the people and project management sides
• Believe that advanced AI systems could have a transformative effect on the world, and are passionate about helping make sure that transformation goes well
• Are an experienced manager (with at least 2 years of recent experience) with a track record of leading high-performing research or engineering teams and actively enjoy people management
• Have at least 5 years of technical experience with research and/or engineering
• Have experience with our research or are motivated to learn more about it
• Enjoy working on an interdisciplinary team (members of our teams have experience across ML, physics, neuroscience, policy, business and product)

Desirable

• As one of the managers on the Interpretability team in Anthropic’s research organization, you'll support a team of expert researchers and engineers who are trying to understand at a deep, mechanistic level, how modern large language models work internally
• Few things can accelerate this work more than great managers
• Your work as manager will be critical in making sure that our fast-growing team is able to meet its ambitious safety research goals over the coming years
• You will manage careers and performance, facilitate relationships within and across teams, and shepherd the hiring pipeline
• While you will not be primarily responsible for setting the research or technical direction, you will work closely with a Technical Research Lead to prioritize and operationalize the agenda. Your primary responsibilities will be people, project and performance management
• Our teams all require a blend of engineering and research expertise to accomplish their goals, and as they grow, need project management and people management support to operate smoothly
• We believe it is too much for one person to sustainably lead in all four of those disciplines for larger teams
• Instead, we prefer to partner Technical Leads with Team Managers to better cover all these expertises
• Some of our team's notable publications include Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet, Towards Monosemanticity: Decomposing Language Models With Dictionary Learning, A Mathematical Framework for Transformer Circuits, In-context Learning and Induction Heads, and Toy Models of Superposition
• This work builds on ideas from members' work prior to Anthropic such as the original circuits thread, Multimodal Neurons, Activation Atlases, and Building Blocks
• Our research has recently led to the discovery of multilingual features in large language mode
• We are actively scaling dictionary learning to larger models and exploring novel approaches to understanding and mitigating obstacles to interpretability like superposition
• Partner with a Technical Research Lead to prioritize the team's work in alignment with our overall research strategy and goals
• Identify improvements to processes (e.g. research reviews, reading groups, code reviews) and implement solutions that help the team operate effectively
• Coach and support your direct reports in their professional growth and development
• Run the team's recruiting efforts efficiently, ensuring we can grow rapidly through a period of significant expansion
• Communicating team updates and results to other teams and leadership