Reinforcement Learning Engineer

Bugcrowd

5d • $176,400 - $242,550 • Remote

About The Position

Bugcrowd’s RL and Reasoning Team builds authentic, verifiable reinforcement learning environments for foundational AI companies. The Reinforcement Learning Engineer specializing in Reinforcement Learning from Verifiable Rewards (RLVR) will design and scale automated verification pipelines that turn real-world software vulnerabilities into deterministic reward functions. The role bridges low-level security analysis and LLM reasoning by creating environments where AI agents learn to discover, exploit, and remediate vulnerabilities using verifiable reward signals rather than subjective human feedback.

The work spans fuzzing, dynamic program analysis, system exploitation, and scalable machine-learning infrastructure. The engineer will develop RLVR environments, verification and execution systems, and reproducible sandboxes; collaborate with frontier AI labs; and evaluate AI models on offensive and defensive cybersecurity challenges. The position is remote and work-from-home 100% of the time. The national estimated base salary range is $176,400–$242,550. The role may also be eligible for a discretionary bonus or commission plan, subject to the applicable program rules and performance factors.

Requirements

• Understand RL training workflows used by modern LLM systems, particularly execution-based feedback or Reinforcement Learning from Verifiable Rewards (RLVR).
• Be proficient in Python and low-level systems programming in C.
• Have a solid understanding of software vulnerabilities, binary exploitation, fuzzing methodologies, or program analysis.
• Have experience with DevOps pipelines such as GitHub Actions and reproducible builds such as Docker, BuildKit, or Nix.
• Be comfortable working with Linux systems and low-level debugging.
• Have experience working with or building benchmark environments, such as CTFs, SWE-bench, security challenges, or execution sandboxes.
• Be able to meet the physical requirements of the job, with or without reasonable accommodation, including remaining stationary for 50% of the time and carrying or moving a laptop as needed.

Nice To Haves

• Experience with Rust.
• Experience designing custom reward functions, ground-truth verifiers, or automated grading engines for AI safety and reasoning models.
• Background in low-level program analysis tools, sanitizers such as ASan or MSan, compiler instrumentation, or automated exploit generation tools.
• A track record of participating in or developing competitive cybersecurity benchmarks, CTFs, or open-source AI evaluation frameworks.

Responsibilities

• Design, build, and deploy high-throughput RLVR environments that evaluate LLM action sequences against deterministic execution outcomes.
• Develop automated test harnesses, sandboxes, and verification engines that turn vulnerability research into binary pass/fail reward signals.
• Integrate Bugcrowd’s Mayhem automated analysis platform and real-world vulnerability feeds into scalable, continuous RL environment-generation pipelines.
• Architect safe, isolated, reproducible execution environments using tools such as Docker, BuildKit, or Nix for large numbers of agent-driven exploitation and patching trajectories.
• Collaborate with researchers at frontier AI labs, including Anthropic, OpenAI, and Cohere, to define benchmark formats, observation spaces, and verifiable evaluation metrics for cybersecurity tasks.
• Implement telemetry, ground-truth verification algorithms, and trajectory logging to analyze agent reasoning and prevent reward hacking or false positives.
• Build low-level instrumentation and debugging tools to monitor memory states, process executions, and network behaviors during agent interactions.
• Optimize infrastructure performance and environment reset latency for large-scale parallel sampling and distributed RL training.
• Benchmark and evaluate frontier AI models on offensive and defensive security challenges, including automated fuzzing, exploit payload generation, and patch validation.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Education Level: No Education Listed