Security Engineer / Research Engineer, RL Security

Anthropic•San Francisco, NY

1d•Hybrid

About The Position

Anthropic is hiring a Security Engineer or Research Engineer to help secure reinforcement-learning training systems and the infrastructure they run on. Reinforcement learning powers Claude’s ability to reason, write code, and act autonomously over long horizons. At frontier scale, RL involves a large distributed system in which training, sampling, and environment execution run concurrently across fleets of accelerators and hosts. This is a hands-on engineering role working in the RL codebase and underlying infrastructure alongside the engineers and researchers who build and use these systems. Security work must keep pace with rapidly changing research while preserving system performance and engineering velocity. Anthropic is interested in candidates with depth in security engineering or ML systems and research engineering, and a genuine interest in the other area. Anthropic’s mission is to create reliable, interpretable, and steerable AI systems that are safe and beneficial for users and society. It is a collaborative research organization focused on a small number of large-scale efforts and values impact, empirical research, and strong communication. Anthropic is a public benefit corporation headquartered in San Francisco.

Requirements

Strong software engineering skills in Python and at least one systems language such as Rust, C++, or Go.
Experience designing, building, and operating large-scale distributed systems or production security systems.
Strong understanding of security fundamentals.
Working knowledge of Linux, containers, and cloud infrastructure.
Experience debugging complex problems across many hosts and services.
Ability to reason about tradeoffs among security, performance, and reliability.
Strong written communication skills, including writing design documents.
At least a bachelor’s degree or an equivalent combination of education, training, and/or experience.
A field of study relevant to the role, demonstrated through coursework, training, or professional experience.
Years of experience will correlate with the internal job level requirements.

Nice To Haves

Experience running ML training or inference infrastructure at scale.
Experience with infrastructure security, such as isolation, access control, networking, or identity.
Experience with Kubernetes or other container orchestration, and sandboxed or virtualized code execution at scale.
Experience building observability for large fleets.
Experience supporting research teams or other fast-moving internal users.
Familiarity with reinforcement learning or large language model training workloads.

Responsibilities

Design, build, and operate security controls for RL training systems and their infrastructure.
Work across orchestration, environments, training, and inference as needed.
Review designs and code across the RL stack, identify security problems, and fix them.
Build shared libraries and tools for RL engineers and researchers.
Build observability to understand system behavior.
Work with researchers and performance engineers to ensure security changes preserve training correctness and performance.
Write clear design documents for engineering work.