New Software Engineer, Infrastructure, Interpretability

About the Role:

• The 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, helping define its charter and building the paved path for secure and low-friction research access.

Responsibilities:

• 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 and help take interpretability methods from research code to dependable audit pipelines.

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.
• Strong cross-functional communication skills and curiosity about unfamiliar domains.

Culture:

• Anthropic works as a single cohesive team on a few large-scale research efforts, valuing impact over smaller puzzles.
• We host frequent research discussions and value communication skills highly.