Software Engineer, Infrastructure, Interpretability

The Interpretability team at Anthropic works to understand what's actually happening inside trained models. This role is an early hire on a new infrastructure effort within Interpretability, building the paved path that makes access to frontier models secure by default, private by design, and low-friction for researchers. The work spans security, privacy, data & compute management, and developer experience.

• Design, build, and own shared infrastructure for Interpretability - research environments, data systems, and compute tooling.
• Lead cross-team efforts with agentic engineering, security, compute, and storage platform teams.
• Discover and resolve major organization-wide developer experience issues.
• Help take interpretability methods from research code to dependable audit pipelines.

• Highly proficient in at least one programming language (e.g., Python, Rust, Go, Java) and productive with Python.
• Significant experience building and operating secure and scalable software infrastructure - cloud systems, distributed systems, or developer tooling.
• Strong cross-functional communication skills.
• Curiosity about interpretability research and AI safety.
• Strong candidates may also have experience with cloud infrastructure (GCP or AWS), Kubernetes, networking, infrastructure-as-code, security engineering, data warehousing, large-scale storage, compute schedulers, and developer productivity tooling.

Annual salary range $320,000—$485,000 USD.

Competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and a lovely office space.

Apply via the provided link.