Manufacturing Engineer for AI Benchmark Development [Remote]

Join a pioneering initiative to develop the Industrial Technical Visual Reasoning Benchmark, an evaluation dataset designed to assess AI models'' reasoning capabilities over authentic engineering visuals. This role invites Manufacturing Engineering experts to create benchmark problems that reflect real-world challenges in the field.

As a Manufacturing Engineering Expert, you will:

• Source genuine professional artifacts such as production workflows, factory layouts, and process diagrams.
• Craft problems that require more than text-based answers, ensuring they challenge the reasoning abilities of AI models.
• Determine clear and concise final answers for each problem.
• Develop step-by-step worked solutions that meet professional standards.
• Tag each problem with relevant domain information, artifact type, skill tested, and difficulty level.
• Collaborate with another domain expert for independent review of each problem before finalization.

This is a part-time, remote, hourly position ideal for practicing professionals with hands-on experience in interpreting real manufacturing engineering artifacts. The role emphasizes complex structural, spatial, and multi-step reasoning, moving beyond simplified textbook figures and basic lookup questions.