Software Engineer, Infrastructure, Interpretability

About Anthropic

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.

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 works to understand what's actually happening inside trained models - and applies our best techniques to keep frontier AI safe as it rapidly improves.

Think of us as doing "neuroscience" of neural networks using "microscopes" we build - or reverse-engineering neural networks like binary programs.

• Our Research blog - covering advances including Monosemantic Features and Circuits
• An Intro to Interpretability from our research lead, Chris Olah
• The Urgency of Interpretability from CEO Dario Amodei
• Engineering Challenges Scaling Interpretability - directly relevant to this role
• 60 Minutes segment - see a demo of tooling our team built
• New Yorker article - what it's like to work on one of AI's hardest open problems

This role is an early hire on a new infrastructure effort within Interpretability: you'll help define its charter, not just execute it.

Interpretability Research Requires Deep Access To Frontier Models While Retaining a High Degree Of Research Flexibility. Your Job Is To Build The Paved Path That Makes That Access Secure By Default, Private By Design, And Low-friction For Every Researcher. The Work Spans Four Areas

• Security: design the secure-by-default environments and access patterns that enable deep model access for an organization whose research requires it - done well, the same design improves both our security posture and research productivity.
• Privacy: build data-access patterns that ensure policy adherence as our research moves from theory into practical application
• Data & Compute Management: manage research data at petabyte scale and make efficient use of large accelerator fleets - storage lifecycle, capacity planning, and scheduling.
• Developer experience: agentic engineering, tooling and observability that keep researchers moving fast

In this role, you’ll be deeply embedded alongside Interp Researchers to understand their workflows - building your understanding of the research as you go; at the same time you’ll bridge communication with Anthropic’s wider platform and security teams. Every hour of researcher friction you remove is multiplied across the whole organization, and the infrastructure you build sets the pace at which interpretability results reach real safety decisions.

• Design, build, and own shared infrastructure for Interpretability - research environments, data systems, and compute tooling that researchers rely on daily
• Lead cross-team efforts with our agentic engineering, security, compute, and storage platform teams, so that company-wide solutions serve research needs
• Discover and resolve major organization-wide developer experience issues
• Help take interpretability methods from research code to dependable audit pipelines

• Are highly proficient in at least one programming language (e.g., Python, Rust, Go, Java) and productive with Python
• Have significant experience building and operating secure and scalable software infrastructure - cloud systems, distributed systems, or developer tooling
• Have strong cross-functional communication skills - equally at home working with researchers and with platform and security teams
• Are extremely curious about unfamiliar domains
• Have a strong ability to prioritize the most impactful work and are comfortable operating with ambiguity and…