Research Scientist, 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.

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 using “microscopes” we build, or as treating neural networks as binary computer programs we're trying to "reverse engineer".

We aim to create a solid foundation for mechanistically understanding neural networks and making them safe (see our vision post). In the short term, we have focused on resolving the issue of "superposition" (see Toy Models of Superposition, Superposition, Memorization, and Double Descent, and our May 2023 update), 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.

We often collaborate with teams across Anthropic, such as Alignment Science and Societal Impacts to use our work to make Anthropic’s models safer. We also have an Interpretability Architectures project that involves collaborating with Pretraining.

• Develop methods for understanding LLMs by reverse engineering algorithms learned in their weights
• Design and run robust experiments, both quickly in toy scenarios and at scale in large models
• Create and analyze new interpretability features and circuits to better understand how models work
• Build infrastructure for running experiments and visualizing results
• Work with colleagues to communicate results internally and publicly

• Have a strong track record of scientific research (in any field), and have done some work on interpretability
• Enjoy team science – working collaboratively to make big discoveries
• Are comfortable with messy experimental science. We’re inventing the field as we work, and the first textbook is years away
• You view research and engineering as two sides of the same coin. Every team member writes code, designs and runs experiments, and interprets results
• You can clearly articulate and discuss the motivations behind your work, and teach us about what you’ve learned. You like writing up and communicating your results, even when they’re null
• Familiarity with Python is required for this role

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

The annual compensation range for this role is $350,000 - $850,000 USD.

Minimum education: Bachelor’s degree or an equivalent combination of education, training, and/or experience

Required field of study: A field relevant to the role as demonstrated through coursework, training, or professional experience

Minimum years of experience: Years of experience required will correlate with the…