About this role
Join a project focused on evaluating AI models in the architecture domain, specifically in visual document understanding and instruction-following. This role involves authoring complex, grounded tasks that include a clear ground-truth output and an objective rubric.
Key Responsibilities- Develop and author intricate tasks for AI evaluation.
- Ensure tasks have a clear ground-truth output.
- Create an objective rubric for assessment.
- Expertise in architecture and building design.
- Experience with AI model evaluation is a plus.
- Remote work opportunity.
- Approximately 15, 20 hours per week.
- Available to candidates in the US and Canada.
- Hourly rate of $75.