Software Engineer, Infrastructure, Interpretability

Anthropic•San Francisco, CA

1d•$320,000 - $485,000•Hybrid

About The Position

The Interpretability team at Anthropic works to understand what's actually happening inside trained models and applies techniques to keep frontier AI safe as it rapidly improves. This role is an early hire on a new infrastructure effort within Interpretability, focused on building secure, private, and low-friction access to frontier models for researchers. The work spans four areas: Security (designing secure-by-default environments), Privacy (building data-access patterns for policy adherence), Data & Compute Management (managing research data at petabyte scale and efficient use of accelerator fleets), and Developer Experience (agentic engineering, tooling, and observability). The engineer will be deeply embedded with researchers, understanding their workflows and bridging communication with platform and security teams.

Requirements

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 - equally at home working with researchers and with platform and security teams
Extremely curious about unfamiliar domains
Strong ability to prioritize the most impactful work and are comfortable operating with ambiguity and questioning assumptions
Curious about interpretability research and its role in AI safety (though no research experience is required!)
Care about the societal impacts and ethics of your work

Nice To Haves

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

Responsibilities

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