Offensive Hardware Security Engineer, Platform Security

Anthropic is a public benefit corporation focused on creating reliable, interpretable, and steerable AI systems. We are seeking an Offensive Hardware Security Engineer to join our Platform Security team. This role involves auditing security features in hardware, firmware, bootloaders, operating systems, and attestation systems to identify and remove vulnerabilities from the ground up.

Key responsibilities include:

• Auditing secure boot chains from firmware through OS initialization for diverse hardware platforms (CPUs, BMCs, switches, peripherals, embedded microcontrollers).
• Auditing attestation systems providing cryptographic proof of system state from hardware root of trust through application layer.
• Auditing measured boot implementations and runtime integrity monitoring.
• Integrating security controls with infrastructure teams without impacting training performance.
• Validating security mechanisms before production deployment.
• Conducting firmware vulnerability assessments and penetration testing.
• Building firmware vulnerability assessment pipelines for continuous security monitoring.
• Documenting security architectures and maintaining threat models.
• Collaborating with software and hardware vendors to ensure security capabilities meet exploit mitigation requirements.

Minimum qualifications include hands-on vulnerability auditing on complex systems, experience with secure boot, measured boot, attestation technologies (TPM, Intel TXT, AMD SEV, ARM TrustZone), strong understanding of cryptographic protocols and hardware security modules, experience with UEFI/BIOS or embedded firmware security, proficiency in low-level programming languages (C, Assembly) and systems programming, knowledge of firmware vulnerability assessment and threat modeling, and ability to work across hardware and software boundaries.

Preferred qualifications include 8+ years of experience in systems security with at least 5 years focused on low-level security, ability to audit logic bugs in Rust or Go, reverse engineering binary software, fault injection and side-channel analysis, auditing silicon root of trust, confidential computing technologies, formal verification, talks at top-tier security conferences, experience using LLMs to automate security assessment, and experience securing large-scale HPC or cloud infrastructure.

The annual salary range is $320,000—$405,000 USD. Anthropic expects all staff to be in one of its offices at least 25% of the time. Visa sponsorship is available.