Senior Mathematics Domain Expert — Remote AI Benchmarking

AI Work Expert; United States; Remote; USD 124,000 - 193,000; Full time

Job summary

Mercor is seeking senior mathematicians to improve how frontier AI models reason about real mathematical research. You will review, write problem specifications, and craft rigorous reference solutions and proofs that define what correctness looks like, while designing benchmarks that test genuine improvement.

This fully remote role in the United States requires a PhD in mathematics or a closely related field, a strong publication record, and hands-on experience with large language models to

Qualifications

• PhD in mathematics, applied mathematics, statistics, operations research, or a closely related field.
• Strong record of peer-reviewed publications is a plus.
• Excellent written communication and precise feedback required.
• Hands-on use of large language models to inform judgments.

Responsibilities

• Expert review: assess mathematical tasks and model outputs for rigor and correctness.
• Write precise problem statements, reference solutions, and proofs that define correctness.
• Design benchmarks and evaluation sets for advanced mathematical reasoning.

Skills

AI fluency

Communication

Analytical reasoning

Peer review

Education

PhD in mathematics / applied mathematics / statistics / OR

Job description

Mercor is seeking senior mathematicians to improve how frontier AI models reason about real mathematical research. You will review, write problem specifications, and craft rigorous reference solutions and proofs that define what correctness looks like, while designing benchmarks that test genuine improvement.

This fully remote role in the United States requires a PhD in mathematics or a closely related field, a strong publication record, and hands-on experience with large language models to