Security Engineer Research Engineer RL Security

AI safety and research company building reliable, interpretable, and steerable AI systems, including the Claude product family and developer platform.

Series F+Recently funded0 current maintainers0 active leads
San Francisco, United States
About Anthropic

Anthropic PBC develops frontier AI systems and deploys them through Claude products and the Claude Platform, with a stated focus on safety, interpretability, and steerability.

View jobs by Anthropic

Skills

Candidate Availability

Required and preferred rules are kept separate and reflect the wording in the original posting.

About the Role

You will design, build, and operate security controls for reinforcement learning systems and supporting infrastructure. You will review designs and code, build shared tools and observability, address security issues across the stack, and preserve training correctness and performance.

Requirements

  • Strong Python skills and proficiency in Rust, C++, or Go
  • Experience building and operating large-scale distributed systems or production security systems
  • Security fundamentals knowledge
  • Working knowledge of Linux, containers, and cloud infrastructure
  • Experience debugging complex multi-host and multi-service systems
  • Ability to balance security, performance, and reliability
  • Strong written communication and design documentation
  • Bachelor’s degree or equivalent education, training, and experience

Responsibilities

  • Design, build, and operate security controls for RL training systems
  • Work across orchestration, environments, training, and inference
  • Review designs and code and fix security issues
  • Build shared libraries and tooling
  • Build observability for RL systems
  • Partner with researchers and performance engineers to preserve correctness and performance
  • Write clear design documents

Benefits

  • Visa sponsorship support
  • Optional equity donation matching
  • Generous vacation
  • Parental leave
  • Flexible working hours