Infrastructure Engineer, Interpretability & AI Safety

Anthropic; San Francisco (CA); On-site; USD 190,000 - 270,000; Full time

Job summary

Anthropic in San Francisco is hiring for an Interpretability Infrastructure Engineer to design and own the shared infrastructure for research environments, data systems, and compute tooling used by frontier AI researchers.

You will collaborate across agentic engineering, security, and platform teams to enable secure, scalable access to model weights and experiments, while improving developer experience and productivity for interpretability work.

Qualifications

• Proficient in at least one programming language and productive with Python
• Experience building and operating secure and scalable software infrastructure

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 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

Skills

Python

Rust

Go

Java

Tools

AWS

GCP

Kubernetes

Data warehouses

Job description

Anthropic in San Francisco is hiring for an Interpretability Infrastructure Engineer to design and own the shared infrastructure for research environments, data systems, and compute tooling used by frontier AI researchers.

You will collaborate across agentic engineering, security, and platform teams to enable secure, scalable access to model weights and experiments, while improving developer experience and productivity for interpretability work.