Offensive Cybersecurity Engineers: Build RL Environments for AI Evaluation (Fully Remote)

Terac; United States; Remote; USD 83,000 - 165,000; Full time

Job summary

Terac is building the world's largest pool of vetted human experts for AI research. This role involves designing and implementing complex cybersecurity benchmarks and reinforcement learning environments for offensive security, with remote, hourly engagement.

You will continuously harden environments for rigorous AI safety evaluations, collaborate iteratively with teams, and keep pace with new vulnerabilities, working on long-term hourly projects from anywhere in the United States.

Qualifications

• 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.

Responsibilities

• Work remotely on an hourly basis to design and implement complex cybersecurity benchmarks.
• Create robust reinforcement learning environments tailored for offensive security scenarios.
• Continuously harden these environments to ensure rigorous evaluations for AI systems.
• Engage in ongoing collaboration and iterative development.
• Keep pace with new vulnerabilities.
• Collaborate on a long-term hourly basis to iterate on security scenarios.

Skills

Offensive cybersecurity

Penetration testing

Environment hardening

AI safety interest

Job description

• Work remotely on an hourly basis to design and implement complex cybersecurity benchmarks.
• Create robust reinforcement learning environments tailored for offensive security scenarios.
• Continuously harden these environments to ensure rigorous evaluations for AI systems.
• Engage in ongoing collaboration and iterative development.
• Keep pace with new vulnerabilities.
• Collaborate on a long-term hourly basis to iterate on security scenarios.

Candidate Profile:

• 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.

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.