AI Math Benchmark Architect — Remote

Weekday 1; United States; Remote; USD 84,000 - 106,000; Part time

Job summary

Weekday 1 is seeking expert mathematicians to author and review high-quality academic assessment content for an AI research initiative. The role is fully remote with compensation of $61-$77 per hour.

You will write and verify rigorous MCQs across core mathematics domains and help establish gold-standard benchmarks for AI progression. Candidates will be assigned two task types: Question Authoring or Question Verification, with responsibilities including clarity, precision, and documentation of

Qualifications

• PhD or doctoral candidate in Mathematics or closely related field.
• Strong command of graduate-level mathematical concepts and formal proof writing.
• Experience with rigorous academic problem design or mathematical competition writing is a strong plus.

Responsibilities

• Author original math questions that test deep conceptual understanding and rate difficulty.
• Ensure questions are unambiguous, self-contained, and precisely defined.
• Rate each question's difficulty: Medium, Hard, or Expert.
• Provide 1 correct answer and 9 plausible alternatives.
• Write step-by-step Chain-of-Thought solutions with clear intermediate steps.
• Supply 1-5 academic references per question.

Education

PhD or doctoral candidate in Mathematics

Master's degree considered for exceptional depth

Tools

Rigorous problem-design experience

Graduate-level proof-writing

Job description

Weekday 1 is seeking expert mathematicians to author and review high-quality academic assessment content for an AI research initiative. The role is fully remote with compensation of $61-$77 per hour.

You will write and verify rigorous MCQs across core mathematics domains and help establish gold-standard benchmarks for AI progression. Candidates will be assigned two task types: Question Authoring or Question Verification, with responsibilities including clarity, precision, and documentation of