RLVR Engineer — Verifiable Rewards for AI Security Roles

Bugcrowd Inc.; United States; Remote; USD 176,000 - 243,000; Full time

Job summary

Bugcrowd is seeking a Reinforcement Learning Engineer specializing in RLVR to design and scale automated verification pipelines that convert real-world vulnerabilities into deterministic reward signals. You will bridge low-level security analysis with modern LLM reasoning, building environments where AI agents learn to discover, exploit, and remediate software vulnerabilities with mathematical certainty.

You will work at the intersection of fuzzing, dynamic program analysis, system exploitation,

Qualifications

• Understanding RL training workflows used by modern LLM systems (RLVR).
• Proficiency developing applications in Python and low-level systems programming in C; Rust is a strong plus.
• Experience with DevOps pipelines (GitHub Actions), reproducible builds (Docker, BuildKit, Nix).

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 convert vulnerability research into binary pass/fail signals.
• Integrate Bugcrowd’s Mayhem platform and vulnerability feeds into RL environment pipelines.
• Architect safe, isolated execution environments using Docker, BuildKit, or Nix for thousands of agent-driven trajectories.
• Collaborate with researchers at AI labs to define benchmark formats, observation spaces, and verifiable metrics.
• Implement telemetry, ground-truth verifiers, and trajectory logging to analyze reasoning paths and prevent reward hacking.
• Build low-level instrumentation to monitor memory, processes, and network behaviors during agent interactions.
• Optimize infrastructure performance and environment reset latency for large-scale RL training.

Skills

RLVR

Python

C

Rust

DevOps

Linux

Docker

Build systems

Tools

Docker

BuildKit

Nix

Job description

Bugcrowd is seeking a Reinforcement Learning Engineer specializing in RLVR to design and scale automated verification pipelines that convert real-world vulnerabilities into deterministic reward signals. You will bridge low-level security analysis with modern LLM reasoning, building environments where AI agents learn to discover, exploit, and remediate software vulnerabilities with mathematical certainty.

You will work at the intersection of fuzzing, dynamic program analysis, system exploitation,