Reinforcement Learning Engineer

📋 Description

• Design, build, and deploy high-throughput RLVR (Reinforcement Learning from Verifiable Rewards)
• Develop automated test harnesses, sandboxes, and verification engines that convert complex
• Integrate Bugcrowd’s Mayhem automated analysis platform and real-world vulnerability feeds into
• Architect safe, isolated, and highly reproducible execution environments (using Docker, BuildKit
• Collaborate directly with researchers at frontier AI labs including Anthropic, OpenAI, and Cohere
• Implement precise telemetry, ground-truth verification algorithms, and trajectory logging to

🎯 Requirements

• Understanding of RL training workflows used by modern LLM systems, specifically execution-based
• Proficiency developing applications in Python and low-level systems programming in C, with Rust
• Solid understanding of software vulnerabilities, binary exploitation, fuzzing methodologies, or
• Experience with DevOps pipelines (e.g., GitHub Actions), reproducible builds (Docker, BuildKit
• Experience working with or building benchmark environments (e.g., CTFs, SWE-bench, security

🎁 Benefits

• Discretionary bonus program or commission plan
• Remote work-from-home opportunity