Platform Security Engineering, Operating Systems

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, engineers, policy experts, and business leaders working together to build beneficial AI systems.

About the role

We're looking for an Operating Systems Security Engineer to harden and secure the OS layer of our infrastructure. You'll be responsible for designing and implementing OS-level security controls, from kernel hardening to runtime protection, ensuring our systems can withstand sophisticated attacks while maintaining the performance required for AI model training.

This is a hands-on role where you'll work with cutting-edge hardware and implement novel security solutions for environments that don't exist anywhere else in the world. You'll need to balance extreme security requirements with the operational needs of researchers training models at unprecedented scale.

Key responsibilities

• Design and implement hardened OS configurations for AI workloads across diverse hardware platforms

• Minimize attack surfaces by removing as many unnecessary components as possible from kernelspace and userspace

• Develop kernel security policies using SELinux, AppArmor, and custom Linux Security Modules and runtime enforcement mechanisms

• Implement and maintain full-disk encryption solutions for diverse storage systems

• Build security infrastructure for AI systems, research environments, and production services

• Create OS-level attestation and integrity monitoring systems

• Apply security patches, develop patches for custom kernel modules, and kernel hardening configurations

• Design secure boot processes and trusted execution environments

• Work with container tea

Department: Security