Security Labs Engineer — Frontier AI Security

Anthropic; New York (NY); On-site; USD 320,000 - 485,000; Full time

Job summary

Anthropic invites senior engineers to join Security Labs, tackling high-risk research to harden frontier AI systems. You’ll own security projects end to end, prototype novel isolation and attestation schemes, and work with research and infra teams to validate workflows.

The role emphasizes depth in one domain and the ability to operate across layers. You should have shipped independent work, strong programming skills in Python and at least one of Rust/Go/C++, and a passion for building

Qualifications

• Demonstrated depth in at least one area of software security (firmware/hardware security, cryptography, OS/kernel, formal methods, reverse engineering, cross-domain security).
• Proven track record shipping independent projects or research that impacted the field.

Responsibilities

• Own Security Labs projects end to end from scoping to prototype and hand-off or exit.
• Stand up novel security infrastructure for isolated clusters, attestation chains, hypervisor and runtime work.

Skills

Python

Rust

Go

C/C++

Education

Bachelor's degree or equivalent in relevant field

Job description

Anthropic invites senior engineers to join Security Labs, tackling high-risk research to harden frontier AI systems. You’ll own security projects end to end, prototype novel isolation and attestation schemes, and work with research and infra teams to validate workflows.

The role emphasizes depth in one domain and the ability to operate across layers. You should have shipped independent work, strong programming skills in Python and at least one of Rust/Go/C++, and a passion for building