Security Engineer / Research Engineer, RL Security

Anthropic•Seattle, WA

2d•$320,000 - $405,000•Hybrid

About The Position

Anthropic is hiring an engineer in RL Engineering to help secure the systems used to train Claude through reinforcement learning. At frontier scale, reinforcement-learning runs rely on large distributed systems in which training, sampling, and environment execution happen concurrently across fleets of accelerators and hosts. The role focuses on keeping these systems secure as they scale, while preserving performance and engineering velocity. This is a hands-on position working in the RL codebase and its underlying infrastructure alongside the engineers and researchers who build and use these systems. The environment changes quickly with the research, so security work must adapt at a similar pace. Anthropic is seeking candidates with depth in either security engineering or ML systems/research engineering, together with a genuine interest in the other area.

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 between security, performance, and reliability.
Strong written communication skills, including the ability to write 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.

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 container orchestration such as Kubernetes and with 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 tooling 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 the systems and tools built.