Reinforcement Learning Infrastructure (Cybersecuri
Core
Build infrastructure and tooling to generate large-scale reinforcement learning environments for training next-generation AI systems in cybersecurity.
Role type
Staff Engineer, Reinforcement Learning Infrastructure
Builds
Training environments for frontier AI labs (e.g., Anthropic, OpenAI) to learn vulnerability discovery and exploitation
Domain
AI/ML Infrastructure, Cybersecurity, Systems Engineering
Deliverable
production ML models
Required skills
Reinforcement learning workflows, Linux ML environment construction, Binary exploitation, Python, C, DevOps pipelines, Build systems
Preferred skills
Rust, Fuzzing, Program analysis, CTFs, SWE-bench
Technologies
Python, C, Rust, Docker, Buildkit, Nix, GitHub Actions, Linux
Responsibilities
Design pipelines to ingest software projects and construct training environments, Build reproducible Linux ML environments, Develop applications in Python and C, Debug low-level issues on Linux systems
Seniority
Staff, hands-on IC
