Research Manager, Interpretability
About Anthropic
Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems.
About the Interpretability team:
When you see what modern language models are capable of, do you wonder, "How do these things work? How can we trust them?"
The Interpretability team’s mission is to reverse engineer how trained models work, and Interpretability research is one of Anthropic’s core research bets on AI safety. We believe that a mechanistic understanding is the most robust way to make advanced systems safe.
People mean many different things by "interpretability". We're focused on mechanistic interpretability, which aims to discover how neural network parameters map to meaningful algorithms. Some useful analogies might be to think of us as trying to do "biology" or "neuroscience" of neural networks, or as treating neural networks as binary computer programs we're trying to "reverse engineer".
We recently showed that we could extract millions of meaningful features from Anthropic’s production Claude 3.0 Sonnet model, along with an initial demonstration of how we can use these features to change the model’s behavior by creating “Golden Gate Claude”. Achieving these results required a large engineering effort including optimizing sparse autoencoders (SAEs) across many GPUs, and building tools to visualize millions of features. Work like this is central to our roadmap of using mechanistic interpretability to improve the safety of LLMs like Claude.
A few places to learn more about our work and team are this introduction to Interpretability from our research lead, Chris Olah; a discussion of our work on the Hard Fork podcast produced by the New York Times, and this blog post (and accompanying video) sharing more about some of the engineering challenges we’d had to solve to get these results. 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.
About the role:
As a manager on the Interpretability team, 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. In this role, you will partner closely with an individual contributor research lead to drive the team's success, translating cutting-edge research ideas into tangible goals and overseeing their execution. You will manage team execution, careers and performance, facilitate relationships within and across teams, and drive the hiring pipeline.
If you're more interested in making individual direct technical contributions to our research, feel free to apply to our Research Scientist or Research Engineer roles instead.
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 identifying improvements to processes that help the team operate effectively
- Coach and support team members to have more impact and develop in their careers
- Drive the team's recruiting efforts, including hiring planning, process improvements, and sourcing and closing
- Help identify and support opportunities for collaboration with other teams across Anthropic
- Communicate team updates and results to other teams and leadership
You may be a good fit if you:
- Are an experienced manager (minimum 3-5 years) with a track record of effectively leading highly technical research and/or engineering teams
- Actively enjoy people management
- Have managed technical teams through periods of high ambiguity and change
- Are a quick learner, capable of understanding and contributing to discussions on complex technical topics
- Have experience with our research or are motivated to learn more about it
- Believe that advanced AI systems could have a transformative effect on the world, and are passionate about helping make sure that transformation goes well
Strong candidates may also have:
- A background in machine learning, AI, or a related technical field
- Experience scaling engineering infrastructure
- Strong people management experience, including coaching, performance evaluation, mentorship, and career development
- Excellent project management skills, including prioritization and cross-functional coordination
- Experience recruiting talent for your team including predicting staffing needs, sourcing candidates, designing interview loops, evaluating and interviewing candidates, and closing offers
- Excellent written and spoken communication and interpersonal skills
- Experience working on open-ended, exploratory research agendas aimed at foundational insights
Role Specific Location Policy:
- This role is expected to be in our SF office for 3 days a week.
The expected salary range for this position is:
Logistics
Location-based hybrid policy: Currently, we expect all staff to be in one of our offices at least 25% of the time. However, some roles may require more time in our offices.
Visa sponsorship: We do sponsor visas! However, we aren't able to successfully sponsor visas for every role and every candidate. But if we make you an offer, we will make every reasonable effort to get you a visa, and we retain an immigration lawyer to help with this.
We encourage you to apply even if you do not believe you meet every single qualification. Not all strong candidates will meet every single qualification as listed. Research shows that people who identify as being from underrepresented groups are more prone to experiencing imposter syndrome and doubting the strength of their candidacy, so we urge you not to exclude yourself prematurely and to submit an application if you're interested in this work. We think AI systems like the ones we're building have enormous social and ethical implications. We think this makes representation even more important, and we strive to include a range of diverse perspectives on our team.
How we're different
We believe that the highest-impact AI research will be big science. At Anthropic we work as a single cohesive team on just a few large-scale research efforts. And we value impact — advancing our long-term goals of steerable, trustworthy AI — rather than work on smaller and more specific puzzles. We view AI research as an empirical science, which has as much in common with physics and biology as with traditional efforts in computer science. We're an extremely collaborative group, and we host frequent research discussions to ensure that we are pursuing the highest-impact work at any given time. As such, we greatly value communication skills.
The easiest way to understand our research directions is to read our recent research. This research continues many of the directions our team worked on prior to Anthropic, including: GPT-3, Circuit-Based Interpretability, Multimodal Neurons, Scaling Laws, AI & Compute, Concrete Problems in AI Safety, and Learning from Human Preferences.
Come work with us!
Anthropic is a public benefit corporation headquartered in San Francisco. We offer competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and a lovely office space in which to collaborate with colleagues.