Security Engineer • Mid-Level

Who you are

You have a strong background in systems integrity and security, with experience in designing and implementing security architectures for bare-metal infrastructure. Your expertise in low-level systems security allows you to architect solutions that balance security requirements with performance demands. You are proficient in programming languages such as C and C++, and have hands-on experience with Linux environments. Your familiarity with cloud services, particularly AWS, enhances your ability to integrate security controls effectively. You understand the importance of firmware and bootloader security, and are skilled in developing attestation systems that provide cryptographic proof of system state. You thrive in collaborative environments, working closely with cross-functional teams to ensure the security of AI systems.

Desirable

Experience with embedded systems and microcontrollers is a plus, as is knowledge of runtime integrity monitoring and measured boot implementations. Familiarity with cryptographic protocols and multi-party authorization systems will further strengthen your candidacy. You are detail-oriented and have a proactive approach to identifying and mitigating security vulnerabilities.

What you'll do

In this role, you will design and implement secure boot chains from firmware through OS initialization for diverse hardware platforms, including CPUs, BMCs, and embedded microcontrollers. You will architect attestation systems that provide cryptographic proof of system state, defining trust boundaries and security policies for multi-party authorization systems. Your responsibilities will include developing measured boot implementations and runtime integrity monitoring, as well as creating reference architectures and security requirements for bare-metal deployments. You will integrate security controls with infrastructure teams, ensuring that security measures do not impact the performance of AI training. Prototyping and validating security mechanisms before production deployment will be a key part of your role, as will conducting firmware vulnerability assessments to identify and address potential security risks.

What we offer

Anthropic offers competitive compensation and benefits, including optional equity donation matching, generous vacation and parental leave, and flexible working hours. You will have the opportunity to work in a collaborative office space in San Francisco, where you can engage with a team of committed researchers, engineers, and policy experts. We encourage you to apply even if your experience doesn't match every requirement, as we value diverse perspectives and backgrounds in our mission to create reliable and beneficial AI systems.