Cincinnatus LLC is building capabilities to stress-test frontier AI models. You will work in a red-teaming setup to design and probe multi-step tasks that reveal vulnerabilities, edge cases, and failure modes in cutting-edge AI systems, with approximately 35 hours per week and fully remote work within the United States.
This is a full-time W-2 role, where you collaborate with researchers to turn findings into stronger benchmark tasks, document evidence and reproducible steps, and help the
#J-18808-Ljbffr