Research Engineer, Interpretability
Research & Engineering
hybrid: San Francisco, CA
Salary range $280,000 - $520,000
added Sat Oct 14, 2023
Apply to AnthropicThe Interpretability team at Anthropic is working to reverse-engineer how models work because we believe that a mechanistic understanding is the most robust way to make advanced systems safe. We’re looking for researchers and engineers to join our efforts.
Few things can accelerate this progress more than great infrastructure. As a research engineer, you will build and maintain infrastructure used by the whole team, including yourself. You'll touch all parts of our code and infrastructure, whether that's making the cluster more reliable for our big jobs, improving throughput and efficiency, running and designing scientific experiments, or improving our dev tooling. You’re motivated to understand our research so you can write code that accelerates it.
Our recent progress, presented in Towards Monosemanticity: Decomposing Language Models With Dictionary Learning, makes us believe that the main blocker to LLM interpretability, known as superposition, has transitioned from an open research question to primarily an engineering challenge. We’re interested in hiring for this role now more than ever because we believe strong candidates will significantly advance the state of the art in LLM interpretability.
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.
About Anthropic
Anthropic is an AI safety and research company that’s working to build reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our customers and for society as a whole. Our interdisciplinary team has experience across ML, physics, policy, business and product.
Responsibilities:
- Build infrastructure for running experiments and visualizing results
- Design and run robust experiments, both quickly in toy scenarios and at scale in large models
- Develop methods for understanding LLMs by reverse engineering algorithms learned in their weights
- Work with colleagues to communicate results internally and publicly
You may be a good fit if you:
- Have significant software engineering experience
- Are results-oriented, with a bias towards flexibility and impact
- Pick up slack, even if it goes outside your job description
- Enjoy pair programming (we love to pair!)
- Want to learn more about interpretability research
- Care about the societal impacts of your work
Strong candidates may also have experience with:
- High performance, large-scale ML systems
- GPUs, Kubernetes, Pytorch, or OS internals
- Language modeling with transformers
- Reinforcement learning
- Large-scale ETL
Representative Projects:
- Garcon - a tool which allows researchers to easily access LLMs internals from a jupyter notebook
- ETL pipelines for collecting and analyzing LLM activations at large scale
- Profiling and Optimizing ML Training, including parallelizing to many GPUs
- Make launching ML experiments and manipulating+analyzing the results fast and easy
- Writing a design doc for fault tolerance strategies
- Creating an interactive visualization of attention between tokens in a language model
Familiarity with python is required for this role.
Annual Salary:
- The expected salary range for this position is $280k - $520k USD.
Logistics
Location-based hybrid policy: Currently, we expect all staff to be in our office at least 25% of the time.
Deadline to apply: We expect to be hiring for this role intermittently, but our plan is to hire a few people in the next 2-3 months, and then will likely slow hiring while the team settles. (This opportunity was originally posted early July.)
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.
- 21 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).
- 21 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, in San Francisco, CA, as of the date of publication and may be modified in the future. 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.
Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our customers and for society as a whole.
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.