Offensive Cybersecurity Engineers: Build RL Environments for AI Evaluation

Terac is recruiting offensive cybersecurity experts for a long-term project focused on evaluating frontier AI models. The role involves building and hardening reinforcement learning environments and developing rigorous security benchmarks.

Responsibilities:

• 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

Requirements:

• We welcome offensive cybersecurity engineers, penetration testers, and security researchers with strong technical backgrounds
• Ideal candidates have hands-on experience building secure environments or developing security benchmarks
• Professional experience in offensive cybersecurity or penetration testing
• Strong background in building or hardening technical environments
• Interest in AI safety and model evaluation
• Familiarity with reinforcement learning or AI evaluation frameworks