Power Systems Engineer for AI Visual Reasoning Benchmark [Remote]

Join a unique opportunity to contribute to the development of the Industrial Technical Visual Reasoning Benchmark, an evaluation dataset designed to assess AI models'' reasoning capabilities over authentic engineering visuals. As a Utilities & Power Systems expert, you will play a crucial role in authoring benchmark problems that challenge AI systems to think critically and solve complex engineering scenarios. Key Responsibilities

• Source genuine professional artifacts such as grid diagrams, electrical diagrams, and substation layouts.
• Develop problems that cannot be solved using text alone, ensuring they require deep understanding and reasoning.
• Determine concise and unambiguous final answers for each problem.
• Write step-by-step worked solutions at a professional level.
• Tag each problem with relevant domain, artifact type, skill tested, and difficulty level.
• Collaborate with another domain expert for independent review of each problem before finalization.

• Hands-on experience in reading and interpreting real power systems and utilities artifacts.
• Ability to create complex problems that require structural, spatial, and multi-step reasoning.
• Professional background in utilities and power systems engineering.

This is a part-time, remote, hourly engagement suitable for practicing professionals.

Hourly rate ranges from $70 to $85.

Open to professionals with relevant experience in the field, capable of delivering high-quality benchmark problems.