Engineer for AI Benchmark Development

Help develop rigorous engineering benchmarks that advance AI research by creating and reviewing academic multiple-choice assessments across specialized engineering fields.

You will contribute through either question authoring or question verification. Authors create original, challenging questions in their engineering specialty, assign a difficulty level, and submit them for review. Verifiers assess existing questions for technical accuracy, clarity, rigor, and solvability, make necessary edits, assign difficulty, and document their revisions.

Semiconductor Design and Manufacturing (VLSI), Control Science and Engineering, Mechatronics, Reactor, Plant Design and Separations, Reservoir Engineering and Maintenance, Bioinstrumentation, and Biotechnology.

• Create original questions that assess deep conceptual understanding rather than surface-level recall.
• Ensure every question is self-contained, unambiguous, precisely defined, and includes all information needed to solve it.
• Classify question difficulty as Medium, introductory undergraduate; Hard, advanced undergraduate; or Expert, postgraduate and above.
• Provide one correct answer and nine plausible, subtly incorrect alternatives designed to challenge expert solvers.
• Write step-by-step solutions with clear intermediate reasoning in Markdown.
• Include one to five academic references from reputable sources, such as peer-reviewed journals or university repositories, for each question.
• For verification work, identify and explain issues involving clarity, completeness, precision, or solvability.

• PhD or current doctoral candidacy in Engineering or a closely related field.
• A master''s degree may be considered for applicants with exceptional depth in a specific engineering subdomain.
• Strong command of graduate-level engineering principles, applied mathematics, and relevant domain standards.
• Professional Engineer licensure or relevant industry experience is a strong advantage.
• Excellent written English and the ability to communicate complex technical ideas clearly and concisely.

• Fully remote, asynchronous work.
• Expected commitment of at least 10 hours per week.
• Hourly engagement.

$61 to $77 per hour.