Research Engineer, Interpretability

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.

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 at Anthropic is working to reverse-engineer how trained 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.

We aim to create a solid foundation for mechanistically understanding neural networks and making them safe. In the short term, we have focused on resolving the issue of "superposition" which causes the computational units of the models, like neurons and attention heads, to be individually uninterpretable, and on finding ways to decompose models into more interpretable components. Our subsequent work found millions of features in Sonnet, one of our production language models, represents progress in this direction.

In our most recent work, we develop methods that allow us to build circuits using features and use this circuits to understand the mechanisms associated with a model's computation and study specific examples of multi-hop reasoning, planning, and chain-of-thought faithfulness on Haiku 3.5, one of our production models. This is a stepping stone towards our overall goal of mechanistically understanding neural networks.

• Implement and analyze research experiments, both quickly in toy scenarios and at scale in large models
• Set up and optimize research workflows to run efficiently and reliably at large scale
• Build tools and abstractions to support rapid pace of research experimentation
• Develop and improve tools and infrastructure to support other teams in using Interpretability’s work to improve model safety

• Have 5-10+ years of experience building software
• Are highly proficient in at least one programming language (e.g., Python, Rust, Go, Java) and productive with python
• Have some experience contributing to empirical AI research projects
• Have a strong ability to prioritize and direct effort toward the most impactful work and are comfortable operating with ambiguity and questioning assumptions.
• Prefer fast-moving collaborative projects to extensive solo efforts
• Want to learn more about machine learning research and its applications and collaborate closely with researchers
• Care about the societal impacts and ethics of your work

• Designing a code base so that anyone can quickly code experiments, launch them, and analyze their results without hitting bugs
• Optimizing the performance of large-scale distributed systems
• Collaborating closely with researchers
• Language modeling with transformers
• GPUs or Pytorch

• Building Garcon, a tool that allows researchers to easily access LLMs internals from a Jupyter notebook
• Setting up and optimizing a pipeline to efficiently collect petabytes of transformer activations and shuffle them.
• Profiling and optimizing ML training, including parallelizing to many GPUs
• Make launching ML experiments and manipulating+analyzing the results fast and easy
• Creating an interactive visualization of attention between tokens in a language model

• This role is based in San Francisco office; however, we are open to considering exceptional candidates for remote work on a case-by-case basis.

The expected base compensation for this position is below. Our total compensation package for full-time employees includes equity, benefits, and may include incentive compensation.

$315,000 - $560,000 USD

Education requirements: We require at least a Bachelor's degree in a related field or equivalent experience.

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…