# Software Engineer, Infrastructure, Interpretability

**Company**: Anthropic
**Location**: San Francisco, CA
**Work arrangement**: hybrid
**Experience**: senior
**Job type**: full-time
**Salary**: $320,000-$485,000 USD
**Category**: Engineering
**Industry**: Technology
**Wikidata**: https://www.wikidata.org/wiki/Q116758847

**Apply**: https://job-boards.greenhouse.io/anthropic/jobs/5388612008?utm_source=yubhub.co&utm_medium=jobs_feed&utm_campaign=apply
**Canonical**: https://yubhub.co/jobs/job_528df489-b5c

## Description

Anthropic's mission is to create reliable, interpretable, and steerable AI systems that are safe and beneficial for users and society.

The Interpretability team at Anthropic works to understand what's happening inside trained models and applies techniques to keep frontier AI safe.

As a Software Engineer, Infrastructure, Interpretability, you will be an early hire on a new infrastructure effort within Interpretability, helping define its charter.

Your job is to build the paved path that makes deep model access secure, private, and low-friction for researchers.

The work spans four areas:

- Security: designing secure-by-default environments and access patterns

- Privacy: building data-access patterns that ensure policy adherence

- Data & Compute Management: managing research data at petabyte scale and making efficient use of large accelerator fleets

- Developer experience: building agentic engineering, tooling, and observability

Responsibilities:

- Design, build, and own shared infrastructure for Interpretability

- Lead cross-team efforts with agentic engineering, security, compute, and storage platform teams

- Discover and resolve major organisation-wide developer experience issues

- 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)

- Significant experience building and operating secure and scalable software infrastructure

- Strong cross-functional communication skills

- Curious about unfamiliar domains and able to prioritise impactful work

- Care about the societal impacts and ethics of your work

Strong candidates may also have:

- 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

- Experience with compute schedulers and accelerator fleet management

- Experience building developer productivity tooling and observability stacks

## Skills

### Required
- Python
- Rust
- Go
- Java
- cloud infrastructure
- security engineering
- data warehousing
- compute schedulers

### Nice to have
- GCP
- AWS
- Kubernetes
- infrastructure-as-code
- identity/auth/access management
- sandboxing
- red teaming
- data lifecycle management
- accelerator fleet management
- developer productivity tooling
- observability stacks

---

Source: [Apply at job-boards.greenhouse.io](https://job-boards.greenhouse.io/anthropic/jobs/5388612008?utm_source=yubhub.co&utm_medium=jobs_feed&utm_campaign=apply)