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.
Interpretability research is one of Anthropic’s core research bets on AI safety. We believe that deeply understanding how AI systems work at a mechanistic level is the most robust way to make advanced systems safe. Our Interpretability work touches nearly all parts of our research org and infrastructure, whether that's designing and running scientific experiments, parallelizing big jobs across multiple servers, optimizing complex programs for throughput and efficiency, improving our dev tooling, or collaborating with other research teams to increase the impact and reach of our discoveries.
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.
We currently have three subteams within Interpretability. These 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. While the default is that the Team Manager would be primarily responsible for the people and project management side of the coin, we have seen other splits work successfully.
Recent Work from the Interpretability Team
Some of our team's notable publications include 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 models. We are actively scaling dictionary learning to larger models and exploring novel approaches to understanding and mitigating obstacles to interpretability like superposition.
About Anthropic
Anthropic is an AI safety and research company founded on the premise that the impact of AI might be comparable to that of the industrial and scientific revolutions, as well as a concern that this might not go well. To that end, a significant focus for Anthropic is discovering what models are doing “under the hood” with Interpretability, so that we can properly evaluate and understand model behavior, and so that we can effectively reason about potential deployment risks.
Responsibilities:
You may be a good fit if you:
Strong candidates may also have experience with:
Annual Salary:
Logistics
Location-based hybrid policy: Currently, we expect all staff to be in our office at least 25% of the time.
US visa sponsorship: We do sponsor visas! However, we aren't able to successfully sponsor visas for every role and every candidate; operations roles are especially difficult to support. But if we make you an offer, we will make every effort to get you into the United States, 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.
Compensation and Benefits*
Anthropic’s compensation package consists of three elements: salary, equity, and benefits. We are committed to pay fairness and aim for these three elements collectively to be highly competitive with market rates.
Equity - On top of this position's salary (listed above), equity will be a major component of the total compensation. We aim to offer higher-than-average equity compensation for a company of our size, and communicate equity amounts at the time of offer issuance.
US Benefits - The following benefits are for our US-based employees:
- Optional equity donation matching at a 3:1 ratio, up to 50% of your equity grant.
- Comprehensive health, dental, and vision insurance for you and all your dependents.
- 401(k) plan with 4% matching.
- 22 weeks of paid parental leave.
- Unlimited PTO – most staff take between 4-6 weeks each year, sometimes more!
- Stipends for education, home office improvements, commuting, and wellness.
- Fertility benefits via Carrot.
- Daily lunches and snacks in our office.
- Relocation support for those moving to the Bay Area.
UK Benefits - The following benefits are for our UK-based employees:
- Optional equity donation matching at a 3:1 ratio, up to 50% of your equity grant.
- Private health, dental, and vision insurance for you and your dependents.
- Pension contribution (matching 4% of your salary).
- 22 weeks of paid parental leave.
- Unlimited PTO – most staff take between 4-6 weeks each year, sometimes more!
- Health cash plan.
- Life insurance and income protection.
- Daily lunches and snacks in our office.
* This compensation and benefits information is based on Anthropic’s good faith estimate for this position as of the date of publication and may be modified in the future. Employees based outside of the UK or US will receive a different benefits package. The level of pay within the range will depend on a variety of job-related factors, including where you place on our internal performance ladders, which is based on factors including past work experience, relevant education, and performance on our interviews or in a work trial.
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. We do not have boundaries between engineering and research, and we expect all of our technical staff to contribute to both as needed.
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 based 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.