Remote Reinforcement Learning Systems Engineer

Bugcrowd; United States; On-site; USD 146,000 - 243,000; Full time

Job summary

Bugcrowd's RL and Reasoning Team builds autonomous cybersecurity environments to train next-gen AI systems. As a Staff Engineer, you will advance reinforcement learning development and deliver the infrastructure and tooling that turn real-world vulnerability research into scalable training environments.

This role focuses on pipelines that ingest software projects, analyze them with Bugcrowd’s Mayhem platform, and automatically construct thousands of RL environments used by frontier AI labs.

Qualifications

• Understanding of RL training workflows used by modern LLM systems.
• Experience with DevOps pipelines (e.g., github actions), reproducible builds (docker, buildkit, nix).
• Proficiency in Python and C. Other languages (especially Rust) are a plus.
• Understanding of software vulnerabilities, fuzzing, or program analysis
• Experience with build systems and large open-source codebases
• Comfort working with Linux systems and low-level debugging
• Experience working with benchmark environments (CTFs, SWE-bench, security challenges, etc.)

Responsibilities

• If you enjoy building high-performance systems that power cutting-edge AI research, this role is for you.
• This role focuses on building the systems that generate RL environments, not just the environments themselves. You will design pipelines that ingest software projects, analyze them with Bugcrowd’s Mayhem platform, and automatically construct training environments used by frontier AI labs including Anthropic, OpenAI, and Cohere.
• The ideal candidate is a strong systems engineer who understands Reinforcement learning workflows, system security, and low-level debugging.
• You will build infrastructure that generates thousands of training environments used to train frontier AI systems.

Skills

RL workflows

Security background

Python

C

Rust

Tools

Mayhem platform

Job description

Bugcrowd's RL and Reasoning Team builds autonomous cybersecurity environments to train next-gen AI systems. As a Staff Engineer, you will advance reinforcement learning development and deliver the infrastructure and tooling that turn real-world vulnerability research into scalable training environments.

This role focuses on pipelines that ingest software projects, analyze them with Bugcrowd’s Mayhem platform, and automatically construct thousands of RL environments used by frontier AI labs.