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 these things work and how we can 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 are 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 doing a kind of biology or neuroscience of neural networks using microscopes we build, or as treating neural networks as binary computer programs that we are trying to reverse engineer.

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.

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 large language models 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.
• View research and engineering as two sides of the same coin. Every team member writes code, designs and runs experiments, and interprets results.
• Can clearly articulate and discuss the motivations behind your work, and teach others about what you’ve learned. You like writing up and communicating your results, even when they’re null.
• Familiarity with Python is required.

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.

Annual compensation range: $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 internal job level requirements.

Location‑based hybrid policy: We expect all staff to be in one of our offices at least 25% of the time, though some roles may require more time in offices.

Visa sponsorship: We sponsor visas and will make every effort to obtain a visa if you receive an offer.

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 for collaboration.

To protect yourself from potential scams, remember that Anthropic recruiters only contact you from addresses ending in  Legitimate recruiters will never ask for money, fees, or banking information before your first day. If you’re ever unsure about a communication, don’t click any links—visit  directly for confirmed position openings.

As set forth in Anthropic’s Equal Employment Opportunity policy, we do not discriminate on the basis of any protected group status under any applicable U.S. law.