Skip to content
AI.info

jobs

Security Engineer / Research Engineer, RL Security

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.

Company
Anthropic
Location
San Francisco, CA; New York City, NY; Seattle, WA
Status
Open
Posted
2026-10-20 23:17 UTC

Anthropic is hiring an engineer to handle security for its reinforcement-learning training systems, the distributed stack where training, sampling and environment execution run across large accelerator fleets. The work is hands-on in the RL codebase and the infrastructure beneath it: building security controls, reviewing designs and code, writing shared tooling and observability, and keeping security changes from costing training correctness or performance. Anthropic is hiring either security engineers interested in large-scale ML systems or ML systems engineers interested in security, with Python plus a systems language.

Original job posting