Reinforcement Learning Engineer

The Reinforcement Learning Engineer at Bugcrowd designs and scales automated verification pipelines to transform real-world software vulnerabilities into deterministic reward functions for reinforcement learning from verifiable rewards (RLVR). This role bridges low-level security analysis and modern LLM reasoning models, engineering environments where AI agents learn to discover, exploit, and remediate software vulnerabilities. The position involves collaborating with frontier AI labs to define benchmark formats and evaluating AI model performance across cybersecurity challenges.