AI Model Evaluator

Organization: Rise Research Data LabsLocation: Remote (US-based)Compensation: $80–120/hour, paid per taskStart Date: Immediate About the RoleAs an AI Model Evaluator, you'll help build the next generation of frontier AI by designing hard, terminal-based tasks that current models fail at — then building the automated verifiers that grade whether an AI agent actually solved them. This is a part-time, contract role (1099) with direct impact on how frontier labs measure and improve model performance. ResponsibilitiesDesign difficult, terminal-based tasks in your domain of expertise (Coding, Machine Learning, Systems, Hardware, Security, or Sciences)Build the automated verifier that grades agent outcomes against your taskReview and refine tasks as models improve, closing loopholes and tightening specsGrade model responses and explain your reasoning where judgment is required You're a Fit If You HaveA degree from a top 100 US school; Master's minimum, PhD preferred5+ years of hands-on or professional experience in your domainDeep expertise in Coding, Machine Learning, Systems, Hardware, Security, or SciencesSome reputable published work (e.g., a thesis) is a plus, not requiredUS-based and authorized to work Benefits$80–120/hour, based on experience, task, and domainNo minimum hours — work when it suits youFree access to leading AI tools Questions: careers@riseresearch.com