Platform Security Engineering - Auditor

Anthropic•San Francisco, CA

20h•Hybrid

About The Position

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, engineers, policy experts, and business leaders working together to build beneficial AI systems. We're seeking a vulnerability assessment candidate for platform security. You'll work cross functionally with teams across Anthropic and our partners to assess security features in hardware, firmware, bootloaders, operating systems, and attestation systems to identify and remove vulnerabilities from the ground up. This role requires expertise in low-level systems security and the ability to audit the most security-critical platform elements. This is not a role where you can simply file a ticket and hope that the fixes get into production and stay in production. The role requires taking ownership that everything you find is eliminated fully and correctly in production, including ensuring known vulnerabilities are never reintroduced.

Requirements

Proven track record of conducting hands-on vulnerability auditing on complex, security-critical systems
8+ years of experience in systems security, with at least 5 years focused on low-level security (firmware, bootloaders, and OS kernel-level security)
Hands-on experience with secure boot, measured boot, and 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, bootloader hardening, and chain of trust implementation
Proficiency in low-level programming languages (C, Assembly) and systems programming
Knowledge of firmware vulnerability assessment and threat modeling
Ability to work effectively across hardware and software boundaries
Strong communication and cross functional collaboration skills
Track record of assessing security architectures for complex, distributed systems
We require at least a Bachelor's degree in a related field or equivalent experience.

Nice To Haves

Experience leading teams of auditors while maintaining focus on what the most business-critical and impactful audit targets are.
Capacity to audit for logic bugs in code written in Rust or Go
Ability to find vulnerabilities via reverse engineering in software that is provided only in binary form
Experience performing fault injection & side-channel analysis attacks on hardware
Experience auditing silicon root of trust implementations
Experience auditing confidential computing technologies and hardware-based TEEs
Background in formal verification or security proof techniques
5 or more talks at top-tier security conferences with candidate listed as first author
Experience using LLMs to automate security assessment (including tooling creation)
Experience securing large-scale HPC or cloud infrastructure
Previous work with AI/ML infrastructure security

Responsibilities

Audit secure boot chains from firmware through OS initialization for diverse hardware platforms (CPUs, BMCs, switches, peripherals, and embedded microcontrollers)
Audit attestation systems that provide cryptographic proof of system state from hardware root of trust through application layer
Audit measured boot implementations and runtime integrity monitoring
Integrate security controls with infrastructure teams without impacting training performance
Validate security mechanisms before production deployment
Conduct firmware vulnerability assessments and penetration testing
Build firmware vulnerability assessment pipelines for continuous security monitoring
Document security architectures and maintain threat models
Collaborate with software and hardware vendors to ensure security capabilities meet our requirements for exploit mitigation