Job Details:
Conduct Model Testing and Grading: Run prompts through models and assess preliminary outputs.
Support Benchmarking and Quality Assurance: Collaborate in QA review processes to ensure prompt tasks and rubrics meet rigor, maintaining consistency and reliability before integration into official benchmarks.
Role Highlights
Flexible workload: 10–20 hours, with potential to increase to 40 hours.
Fully remote and asynchronous—work on your own schedule.
Role Start Date
Compensation and Legal Details
You will be legally classified as an hourly contractor for Mercor
We will pay you out at the end of each week via Stripe Connect
Any question or remark? just write us a message
If you would like to discuss anything related to payment, account, licensing,
partnerships, or have pre-sales questions, you’re at the right place.