Remote Offensive Cybersecurity Engineer - AI Safety

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

Benefits offered by this job

Remote work

Job summary

Terac is seeking professionals to design and build offensive cybersecurity reinforcement learning environments and harden benchmarks for advanced AI interactions. You will help develop rigorous evaluation criteria for frontier AI models and collaborate on long-term hourly remote projects.

Ideal candidates have hands-on offensive security or penetration testing experience and a strong background in building secure technical environments, with an interest in AI safety and model evaluation.

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

• 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.

Job description

Terac is seeking professionals to design and build offensive cybersecurity reinforcement learning environments and harden benchmarks for advanced AI interactions. You will help develop rigorous evaluation criteria for frontier AI models and collaborate on long-term hourly remote projects.

Ideal candidates have hands-on offensive security or penetration testing experience and a strong background in building secure technical environments, with an interest in AI safety and model evaluation.