jobs

Offensive Hardware Security Engineer, Platform Security

About Anthropic Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers,

Company

Anthropic

Location

San Francisco, CA; New York City, NY; Seattle, WA

Status

Closed

Posted

2026-07-10T20:04:07+00:00

Anthropic is hiring an offensive hardware security engineer for its platform security group, based in San Francisco, New York City or Seattle. The work is auditing secure boot chains, attestation and measured boot from firmware through OS initialisation on CPUs, BMCs, switches and embedded microcontrollers, running firmware penetration tests, building continuous assessment pipelines, and owning that every finding is fixed in production and never reintroduced. It asks for hands-on low-level security experience, C and Assembly, and TPM, Intel TXT, AMD SEV or ARM TrustZone knowledge. Preferred extras include fault injection, side-channel analysis and LLM-assisted security tooling.