Platform Security Engineering, Auditor

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.

• →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

• Proven track record of conducting hands-on vulnerability auditing on complex, security-critical systems
• 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

• 8+ years of experience in systems security, with at least 5 years focused on low-level security (firmware, bootloaders, and OS kernel-level security)
• 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

Minimum education: Bachelor’s degree or an equivalent combination of education, training, and/or experience

Required field of study: A field relevant to the role as demonstrated through coursework, training, or professional experience

Minimum years of experience: Years of experience required will correlate with the internal job level requirements for the position

Location-based hybrid policy: Currently, we expect all staff to be in one of our offices at least 25% of the time. However, some roles may require more time in our offices.

Visa sponsorship: We do sponsor visas! However, we aren't able to successfully sponsor visas for every role and every candidate. But if we make you an offer, we will make every reasonable effort to get you a visa, and we retain an immigration lawyer to help with this.

We encourage you to apply even if you do not believe you meet every single qualification. Not all strong candidates will meet every single qualification as listed.  Research shows that people who identify as being from underrepresented groups are more prone to experiencing imposter syndrome and doubting the strength of their candidacy, so we urge you not to exclude yourself prematurely and to submit an application if you're interested in this work. We think AI systems like the ones we're building have enormous social and ethical implications. We think this makes representation even more important, and we strive to include a range of diverse perspectives on our team.

Your safety matters to us. To protect yourself from potential scams, remember that Anthropic recruiters only contact you from @anthropic.com email addresses. In some cases, we may partner with vetted recruiting agencies who will identify themselves as working on behalf of Anthropic. Be cautious of emails from other domains. Legitimate Anthropic recruiters will never ask for money, fees, or banking information before your first day. If you're ever unsure about a communication, don't click any links—visit anthropic.com/careers directly for confirmed position openings.

We believe that the highest-impact AI research will be big science. At Anthropic we work as a single cohesive team on just a few large-scale research efforts. And we value impact — advancing our long-term goals of steerable, trustworthy AI — rather than work on smaller and more specific puzzles. We view AI research as an empirical science, which has as much in common with physics and biology as with traditional efforts in computer science. We're an extremely collaborative group, and we host frequent research discussions to ensure that we are pursuing the highest-impact work at any given time. As such, we greatly value communication skills.

The easiest way to understand our research directions is to read our recent research. This research continues many of the directions our team worked on prior to Anthropic, including: GPT-3, Circuit-Based Interpretability, Multimodal Neurons, Scaling Laws, AI & Compute, Concrete Problems in AI Safety, and Learning from Human Preferences.

Anthropic is a public benefit corporation headquartered in San Francisco. We offer competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and a lovely office space in which to collaborate with colleagues. Guidance on Candidates' AI Usage: Learn about our policy for using AI in our application process.