Offensive Cybersecurity Engineer - AI Evaluation Environments (Remote - US only)

Pay: $150/hr - $150/hr (hourly rate). A company that supplies vetted human experts to AI research teams is hiring offensive security specialists for a long-term paid project on AI evaluation. The work centers on building and strengthening reinforcement learning environments that measure how capable frontier AI models are at offensive security tasks. The engagement is hourly and runs on an ongoing basis as new vulnerabilities and scenarios emerge.

What you'll do

• Design and build offensive cybersecurity reinforcement learning environments and scenarios
• Harden existing security benchmarks so they hold up against advanced AI interactions
• Develop rigorous evaluation criteria for judging frontier AI model performance
• Iterate on security scenarios in collaboration with the project team as threats evolve

What you need

• Professional experience in offensive cybersecurity, penetration testing, or security research
• Strong background building or hardening technical environments or security benchmarks
• Must be located in and authorized to work from the United States
• Ability to commit to a long-term hourly contract and work remotely
• Interest in AI safety and model evaluation; prior reinforcement learning or AI evaluation experience is a plus but not required

Applicants must be based in: United States.

How to apply

Get the free i'llTip app to see the employer's details and apply. i'llTip's AI can tailor your résumé to this job, and you'll get alerts for similar roles.

Prefer the website? Continue on illtip.comOr get the app: Android · iPhone

🔔 Get new jobs like this first: join i'llTip Jobs on Telegram · or get personal job alerts