Offensive Cybersecurity Engineers: Build RL Environments for AI Evaluation

Ali Aydi; United States; Remote; USD 170,000 - 243,000; Full time

Job summary

Terac is seeking offensive cybersecurity experts to design and implement reinforcement learning environments that test frontier AI models. This remote, hourly long-term project focuses on building and hardening benchmarks to rigorously evaluate AI security systems.

Ideal candidates have hands-on experience in offensive cybersecurity or pentesting, with a strong technical background and interest in AI safety. We offer remote, hourly collaboration on ongoing security scenarios.

Qualifications

• Hands-on experience building secure environments or developing security benchmarks.
• Background in offensive cybersecurity or penetration testing.
• Familiarity with reinforcement learning or AI evaluation frameworks is valued but not required.

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 remote project to iterate on security scenarios.

Skills

Offensive cybersecurity

Penetration testing

Security research

Reinforcement learning

AI evaluation

Job description

We're hiring offensive cybersecurity experts for a long-term paid project focused on AI evaluation. Our goal is to build and harden reinforcement learning environments that test the limits of frontier AI models. This work directly contributes to understanding and mitigating advanced security risks in emerging technologies.

How It Works

You will work remotely on an hourly basis to design and implement complex cybersecurity benchmarks. Your tasks will involve creating robust reinforcement learning environments tailored for offensive security scenarios. You will continuously harden these environments to ensure they provide rigorous evaluations for AI systems. The project requires ongoing collaboration and iterative development to keep pace with new vulnerabilities.

Who This Is For

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. Familiarity with reinforcement learning or AI evaluation frameworks is highly valued but not strictly required.

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

Who Should Apply

• 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

Compensation

$150 per hour

About Terac

Terac is building the world's largest pool of vetted human experts for AI. Researchers, AI labs, and product teams use Terac to recruit, screen, and pay study participants across industries, languages, and skill sets.

Learn more at terac.com or on YouTube at @jointerac.

Details

Who may apply USA Only As the board states it — check the description for country or time‑zone limits.