Benchmark Designer: Computational Statistics & Applied Math

Mercor; New York (NY); On-site; USD 60,000 - 110,000; Part time

Benefits offered by this job

Flexible hours

Challenging bench-work

Job summary

Mercor is seeking a Computational Statistics and Applied Mathematics Expert to design graduate-level problems that test AI systems on real scientific workflows. You'll craft challenges using specialized software, run simulations, and interpret results.

Youll collaborate with statisticians and data scientists, emphasize problem design over brute force math, and contribute to benchmarks that probe AI reasoning and reproducibility.

Qualifications

• Graduate-level training in statistics or applied mathematics.
• Proven proficiency with at least one specialized software package, demonstrated through publications, open-source contributions, or professional work.
• Strong Python skills — you'll write problem setups, oracle functions, and validators.
• Ability to work independently and refine problem designs based on feedback.
• Comfortable in a Linux/terminal environment with remote compute sandboxes.
• Available for 15–20 hours per week.

Responsibilities

• Design problems requiring skilled use of specialized statistical or scientific software.
• Create multi-step workflows and strategies to uncover information from data.
• Iterate problems with testing against state-of-the-art AI models.

Skills

Python programming

Linux / terminal

Problem design

Graduate-level statistics

Education

Graduate degree in statistics or applied mathematics

Tools

R

Scilab

Matlab

Job description

Mercor is seeking a Computational Statistics and Applied Mathematics Expert to design graduate-level problems that test AI systems on real scientific workflows. You'll craft challenges using specialized software, run simulations, and interpret results.

Youll collaborate with statisticians and data scientists, emphasize problem design over brute force math, and contribute to benchmarks that probe AI reasoning and reproducibility.