RL Security Engineer for Large-Scale ML Systems

Anthropic; San Francisco (CA); Hybrid; USD 320,000 - 405,000; Full time

Job summary

Anthropic, a leading AI safety company in San Francisco, is seeking an RL Engineering security-focused engineer to safeguard large-scale RL systems.

You will design, build, and operate security controls across RL training, environments, and infrastructure, collaborating with researchers to maintain safety and performance.

Strong candidates have solid Python and systems language skills, experience with distributed systems, and deep knowledge of security fundamentals, Linux, containers, and cloud.

Qualifications

• 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 security systems in production
• 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, including design documents

Responsibilities

• Design, build, and operate security controls for RL training systems and the infrastructure they run on
• Work across the stack (orchestration, environments, training, inference) wherever the work is needed
• Review designs and code across the RL stack, find security problems, and fix them
• Build shared libraries and tooling that other RL engineers and researchers build on
• Build the observability needed to understand what these systems are doing
• Work with researchers and performance engineers to make sure security changes preserve training correctness and performance
• Write clear design documents for what you build

Skills

Python

Rust

C++

Go

Security fundamentals

Distributed systems

Linux knowledge

Containers

Cloud infrastructure

Debugging complex systems

Design documents

Education

Bachelor’s degree in a relevant field

Tools

Kubernetes

Job description

Anthropic, a leading AI safety company in San Francisco, is seeking an RL Engineering security-focused engineer to safeguard large-scale RL systems.

You will design, build, and operate security controls across RL training, environments, and infrastructure, collaborating with researchers to maintain safety and performance.

Strong candidates have solid Python and systems language skills, experience with distributed systems, and deep knowledge of security fundamentals, Linux, containers, and cloud.