Reinforcement Learning Engineer

🔥 0 minutes ago

🇺🇸 United States – Remote

💵 $176.4k - $242.6k / year

⏰ Full Time

🟡 Mid-level

🟠 Senior

👷🏻‍♀️ Engineer

👻 Ghost score 1%

What it means: how likely this posting is sitting open without active hiring.How to read it: 60% or higher means we think this is a ghost. Lower scores are less of a worry.How we score it: age, reposts, open roles vs team size, how fast jobs close, and whether pay is listed.Fine print: an estimate from public data, not a judgment of the company. Real jobs can score high, so treat it as a hint, not a fact.

Apply Now

Find Similar Remote Jobs

Set Up Email Alert For New Jobs

📊 Check your resume score for this job

Improve your chances of getting an interview by checking your resume score before you apply.

Upload Resume

Bugcrowd

WebsiteLinkedInAll Job Openings

201 - 500 employees

Founded 2012

💼 Consulting

🏥 Healthcare

📦 Logistics

💰 $30M Series D on 2020-04

Consulting • Healthcare • Logistics

Bugcrowd is a leading platform that provides continuous security testing solutions, enabling organizations to stay ahead of cyberthreats. By leveraging a global community of trusted security researchers, Bugcrowd offers services such as penetration testing as a service, vulnerability disclosure, bug bounty programs, and attack surface management. The company assists industries such as financial services, healthcare, and technology in identifying and prioritizing vulnerabilities, ensuring proactive protection against potential cyber attacks. Driven by data and AI, Bugcrowd's comprehensive approach integrates seamlessly with existing systems to streamline the remediation of security issues, enhancing the overall security posture of its clients.

📋 Description

• Design, build, and deploy high-throughput RLVR environments evaluating LLM action sequences against deterministic execution outcomes • Develop automated test harnesses, sandboxes, and verification engines that convert vulnerability research into binary pass/fail reward signals • Integrate Bugcrowd’s Mayhem automated analysis platform and real-world vulnerability feeds into scalable RL environment generation pipelines • Architect safe, isolated, reproducible execution environments using Docker, BuildKit, or Nix • Collaborate with researchers at Anthropic, OpenAI, and Cohere to define benchmark formats, observation spaces, and verifiable evaluation metrics • 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 for memory states, process executions, and network behaviors • Optimize infrastructure performance and environment reset latency for large-scale parallel sampling and distributed RL training • Benchmark frontier AI models across offensive and defensive security challenges including automated fuzzing, exploit payload generation, and patch validation

🎯 Requirements

• Understanding of RL training workflows used by modern LLM systems, specifically execution-based feedback or Reinforcement Learning from Verifiable Rewards (RLVR) • Proficiency developing applications in Python • Proficiency in low-level systems programming in C • Rust experience is a strong plus • Solid understanding of software vulnerabilities, binary exploitation, fuzzing methodologies, or program analysis • Experience with DevOps pipelines such as GitHub Actions • Experience with reproducible builds using Docker, BuildKit, or Nix • Comfort working with Linux systems and low-level debugging • Experience working with or building benchmark environments such as CTFs, SWE-bench, security challenges, or execution sandboxes • Preferred: experience designing custom reward functions, ground-truth verifiers, or automated grading engines for AI safety and reasoning models • Preferred: background in low-level program analysis tools, sanitizers such as ASan/MSan, compiler instrumentation, or automated exploit generation tools • Preferred: track record of participating in or developing competitive cybersecurity benchmarks, CTFs, or open-source AI evaluation frameworks • Ability to complete all physical requirements with or without reasonable accommodation • Ability to remain in a stationary position 50% of the time • Ability to carry or move a laptop as needed throughout the work day • Integrity to maintain confidential information in the strictest confidence • Successful completion of applicable background checks

🏖️ Benefits

• Discretionary bonus program or commission plan eligibility • Reasonable accommodation for disabilities • Work-from-home arrangement