Role OverviewMercor connects elite creative and technical talent with leading AI research labs. As a STEM Expert Task Pilot, you will build challenging, real-world tasks to test AI agents on expert-level technical work.
What You Will Do
Design open-ended tasks with no single right answer, allowing for partial credit scoring. Develop tasks like 'Build the fastest possible attention engine' to push AI capabilities. Ensure tasks are evaluated automatically from 0 to 1 with partial credit.
Why It Might Be a Fit
You must have expertise in your field to create high-level technical tasks and the ability to design tasks that challenge AI models.
Requirements
- Expertise in your field to create high-level technical tasks
- Ability to design tasks that challenge AI models
]]>