Staff+ Software Engineer, Infrastructure, Interpretability

Anthropic's Interpretability team works to understand what's actually happening inside trained models and applies techniques to keep frontier AI safe. This role is an early hire on a new infrastructure effort within Interpretability, helping define its charter. The work spans four areas: security (secure-by-default environments and access patterns), privacy (data-access patterns ensuring policy adherence), data & compute management (petabyte-scale research data, accelerator fleets, storage lifecycle, capacity planning, scheduling), and developer experience (agentic engineering, tooling, observability). You'll be embedded with Interpretability researchers to understand their workflows and bridge communication with Anthropic's wider platform and security teams.

• 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

You may be a good fit if you:

• 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
• Are extremely curious about unfamiliar domains
• Have a strong ability to prioritize impactful work and operate with ambiguity
• Are curious about interpretability research and its role in AI safety (no research experience required)
• Care about societal impacts and ethics of your work

Strong candidates may also have:

• Experience with cloud infrastructure (e.g., GCP or AWS), Kubernetes, networking, infrastructure-as-code
• Security engineering experience: identity/auth/access management, sandboxing, red teaming
• Experience with data warehousing, large-scale storage systems, data lifecycle management
• Experience with compute schedulers and accelerator fleet management
• Experience building developer productivity tooling and observability stacks
• Experience building tooling to accelerate research teams

Annual salary: $405,000—$485,000 USD.

Apply through the Greenhouse job posting. Anthropic encourages applications even if you don't meet every qualification. Note: Anthropic recruiters only contact from @anthropic.com addresses; be cautious of scams.