Offensive Cybersecurity Engineers: Build RL Environments for AI Evaluation

Terac

1d • Remote

About The Position

Terac is hiring offensive cybersecurity experts for a long-term paid project focused on AI evaluation. The work involves building and hardening reinforcement learning environments to test frontier AI models and contribute to understanding and mitigating advanced security risks in emerging technologies.

The role is remote and hourly. You will design and implement complex cybersecurity benchmarks, create robust reinforcement learning environments for offensive security scenarios, and continuously harden them to provide rigorous evaluations of AI systems. The project involves ongoing collaboration and iterative development to keep pace with new vulnerabilities.

Requirements

• Professional experience in offensive cybersecurity or penetration testing.
• Strong background in building or hardening technical environments.
• Comfortable working on long-term hourly remote projects.
• Interest in AI safety and model evaluation.

Nice To Haves

• Familiarity with reinforcement learning or AI evaluation frameworks.
• Hands-on experience building secure environments or developing 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.

What This Job Offers

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