Remote AI Evaluation Security Engineer (Offensive)

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

Benefits offered by this job

Remote work

Hourly pay

Long-term project

Job summary

Terac is hiring offensive cybersecurity experts to design and implement reinforcement learning-based benchmarks for AI evaluation. The role is remote and paid hourly, focusing on building hardening environments and evaluating frontier AI models.

Ideal candidates have hands-on experience with secure environments, security benchmarks, and a strong background in offensive security. Collaboration on a long-term hourly basis is required to iterate on evolving scenarios.

Qualifications

• Hands-on experience building secure environments or developing security benchmarks.
• Strong technical background in offensive cybersecurity or pentesting.
• Interest in AI safety and model evaluation is valued.

Responsibilities

• Design and build offensive cybersecurity reinforcement learning environments.
• Harden 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.

Skills

Offensive cybersecurity

Penetration testing

Security research

AI safety

Tools

Reinforcement learning

AI evaluation frameworks

Job description

Terac is hiring offensive cybersecurity experts to design and implement reinforcement learning-based benchmarks for AI evaluation. The role is remote and paid hourly, focusing on building hardening environments and evaluating frontier AI models.

Ideal candidates have hands-on experience with secure environments, security benchmarks, and a strong background in offensive security. Collaboration on a long-term hourly basis is required to iterate on evolving scenarios.