Overview
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.
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.
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
Requirements
- 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
- Familiarity with reinforcement learning or AI evaluation frameworks (highly valued but not required)
Compensation
- $150 per hour
Application
Start your paid interview now (https://terac.com/interview/start/r/2d47648e-78c7-4b8c-b9d2-d1f1d4de98ba?utm_source=ashby_listing_description)
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 (https://terac.com) or on YouTube at @jointerac (https://www.youtube.com/@jointerac).
Imported from Terac’s job posting on jobs.ashbyhq.com. Apply sends you to the original listing.