Staff Software Security Engineer — Breakthrough AI Security

Anthropic Limited; San Francisco (CA); Hybrid; USD 320,000 - 485,000; Full time

Benefits offered by this job

Equity donation matching

Generous vacation and parental leave

Flexible working hours

Office space in San Francisco

Job summary

Anthropic Security Labs is seeking a senior security-focused engineer to lead high‑risk, high‑value research projects. You will own specifications, prototype secure systems, and validate them against real workloads, with a strong emphasis on isolations and cryptographic proofs.

You’ll collaborate across research, infra, and compute teams, delivering scalable security architectures and costed contingency plans that advance Anthropic's mission for safe and steerable AI.

Qualifications

• Strong software engineering background with depth in at least one high‑assurance area.
• Proven ability to ship on complex security projects and collaborate with researchers.
• Experience across multiple layers of the stack and ability to dive into new domains.

Responsibilities

• Own Security Labs projects end to end, scope bets, prototype, test, and hand off or exit.
• Stand up novel security infra fast, including isolated clusters and attestation chains.
• Collaborate with research and infra teams to validate workflows and document gaps.
• Turn results into writeups and costed contingency plans for future bets.
• Help select next bets and influence industry security directions.
• Communicate clearly and drive defense-focused outcomes.

Skills

Python

Rust

Go

C/C++

Kernel internals

Formal methods

Reverse engineering

Security engineering

Education

Bachelor's degree

Tools

Virtual Machines

Hypervisor

Attestation chains

Job description

Anthropic Security Labs is seeking a senior security-focused engineer to lead high‑risk, high‑value research projects. You will own specifications, prototype secure systems, and validate them against real workloads, with a strong emphasis on isolations and cryptographic proofs.

You’ll collaborate across research, infra, and compute teams, delivering scalable security architectures and costed contingency plans that advance Anthropic's mission for safe and steerable AI.