Security Engineer for Scalable RL ML Systems

Anthropic Limited

San Francisco, New York, Seattle (CA, NY, WA)

In loco

USD 320.000 - 405.000

Tempo pieno

2 giorni fa

Candidati tra i primi

Aumenta le possibilità di ricevere una risposta da questo datore di lavoro

Il tuo curriculum e una lettera di presentazione personalizzati, che corrispondono esattamente a ciò che sta cercando.

Supera i filtri ATS

Descrizione del lavoro

Anthropic is hiring for a Security Engineer / Research Engineer (RL Security) to secure large-scale RL training systems and infrastructure in our San Francisco offices. You will design, deploy, and operate security controls across the RL stack, collaborating with researchers and performance engineers to maintain training correctness and velocity.

The role emphasizes strong Python and systems programming skills (Rust/C++/Go), experience with distributed systems, and a deep understanding of

Competenze

Bachelor's degree or equivalent in a relevant field.
Strong Python and systems language experience (Rust, C++, or Go).
Experience designing, building, and operating large-scale distributed systems or security systems.
Solid knowledge of security fundamentals and Linux/container environments.
Experience debugging complex distributed systems across many hosts.
Able to balance security, performance, and reliability trade-offs.

Mansioni

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.