Offensive Cybersecurity Engineers: Build RL Environments for AI Evaluation

Overview

Design, build and harden offensive cybersecurity reinforcement learning environments and benchmarks used to evaluate frontier AI models.

What you'll do

• Design and build offensive cybersecurity reinforcement learning environments
• Harden existing benchmarks to withstand advanced AI interactions
• Develop rigorous evaluation criteria for frontier AI models
• Collaborate on a long-term hourly basis to iterate on security scenarios

What you'll need

• Professional experience in offensive cybersecurity or penetration testing
• Strong background in building or hardening technical environments
• Hands-on experience building secure environments or developing security benchmarks

Nice to have

• Familiarity with reinforcement learning or AI evaluation frameworks

Details

• Remote, hourly, long-term paid project
• Compensation: $150 per hour