Summary

This role engages an operations subject matter expert to design realistic workflow problems and evaluate AI systems against professional business operations work. It can be performed remotely or from Aptura's Liverpool Street, London office, with compensation of $400 for selected task ideas and $100 per hour for evaluation and rubric design.

Responsibilities

• Design workflow problems for AI model testing
• Create business review and rollout materials
• Define precise grading criteria for outputs
• Evaluate AI systems on real operations work
• Work with research teams on implementation