Remote AI Math Benchmark Architect

Mercor; United States; Remote; USD 60,000 - 100,000; Full time

Job summary

Mercor is seeking expert mathematicians to author and review high-quality academic assessment content for an AI research initiative. You will write and verify rigorous multiple-choice questions across core mathematics domains, evaluate solution quality, and help establish gold-standard benchmarks used to advance AI capabilities.

You will be assigned one of two task types: Question Authoring or Question Verification, work asynchronously, fully remote, and commit to 10+ hours per week.

Qualifications

• PhD or doctoral candidate in Mathematics, Applied Mathematics, Statistics, or a closely related field.
• Excellent written English and ability to express complex ideas clearly and concisely.
• Experience with rigorous academic problem design or mathematical competition writing is a strong plus.

Responsibilities

• Author original math questions that test deep conceptual understanding, not surface-level recall.
• Rate each question's difficulty: Medium (intro undergraduate), Hard (advanced undergraduate), or Expert (post-graduate and above).
• Provide 1 correct answer and 9 plausible but subtly incorrect alternatives that challenge expert-level solvers
• Write step-by-step Chain-of-Thought solutions with clear, concise intermediate steps in markdown format
• Supply 1-5 academic references per question from reputable sources (peer-reviewed journals, university repositories)
• For verification tasks: flag issues with clarity, completeness, precision, or solvability and justify any edits made

Skills

Graduate-level math concepts

Formal proof writing

Education

PhD in Mathematics

PhD candidate

Job description

Mercor is seeking expert mathematicians to author and review high-quality academic assessment content for an AI research initiative. You will write and verify rigorous multiple-choice questions across core mathematics domains, evaluate solution quality, and help establish gold-standard benchmarks used to advance AI capabilities.

You will be assigned one of two task types: Question Authoring or Question Verification, work asynchronously, fully remote, and commit to 10+ hours per week.