Mercor
$60–90/hr
141 people hired
You will design complex, multi-step AI benchmark tasks based on real computational research workflows. | The role translates experimental design, hypothesis testing, coding, simulation, data analysis, and scientific evaluation into rigorous tasks for frontier AI models. | You will create reference solutions and evaluate model attempts for methodological and reasoning errors. | This is a full-time W-2 role, fully remote within the United States.
Computational STEM Research Expert