Math Expert - Terminal Bench

Overview

ExpertWoka is sourcing Mathematics Experts to develop realistic, terminal-based scientific tasks for a benchmark focused on mathematical reasoning, computation, and validation.

What You'll Do

• Design authentic, multi-step computational mathematics tasks.
• Translate mathematical and research workflows into self-contained terminal environments.
• Prepare datasets, equations, model definitions, constraints, initial conditions, and expected outputs.
• Implement expert solutions using Python, R, Julia, C/C++, Bash, or other relevant tools.
• Create tasks involving optimization, numerical integration, differential equations, matrix computation, statistical inference, stochastic modeling, or algorithm analysis.
• Define rigorous grading criteria based on numerical accuracy, convergence, complexity, feasibility, and mathematical correctness.
• Establish appropriate tolerances, stopping criteria, stability requirements, and reproducibility controls.
• Develop automated tests that validate results across edge cases and alternative valid implementations.
• Debug issues involving floating-point precision, solver failures, conditioning, convergence, and performance.
• Document assumptions, mathematical formulations, expected outputs, and known limitations.

Requirements

• Ph.D., postdoctoral experience, or equivalent advanced technical experience in mathematics, statistics, or a closely related discipline.
• Strong programming skills in Python, R, Julia, C/C++, Bash, or another relevant language.
• Experience working in Linux or terminal-based environments.
• Experience with numerical methods, optimization, statistics, mathematical modeling, or scientific computation.
• Ability to independently implement, test, and validate computational algorithms.
• Strong understanding of numerical stability, error analysis, mathematical assumptions, and reproducibility.

Preferred Qualifications

• Experience with NumPy, SciPy, SymPy, pandas, scikit-learn, JAX, PyTorch, CVXPY, or similar tools.
• Familiarity with optimization solvers, probabilistic programming, differential-equation libraries, or numerical linear algebra packages.
• Experience with Monte Carlo methods, stochastic processes, Bayesian inference, graph algorithms, or computational geometry.
• Familiarity with Docker, Conda, Git, CI systems, and automated testing.
• Experience developing mathematical programming challenges, benchmark tasks, or automated graders.
• Experience evaluating AI coding or terminal agents.
• Research software engineering experience.
• Experience working with HPC or performance-critical numerical code.
• Publications or open-source contributions in applied mathematics or computational science.
• Experience designing tests that distinguish mathematically valid solutions from approximate or numerically unstable ones.

Schedule

• Full-time contractor assignment.
• 40 hours per week.
• 4 hours PST overlap per day.
• Engagement length: 5 weeks.
• Start date: Immediate.

Project Details

• Average task handling time: 6-8 hours.
• Payment is per approved task.

Evaluation Process

• Interest Check Form (ICF).
• Assessment - 60 mins.
• Delivery Manager Review.
• Mandatory screening test: Terminal Bench - Screening Test - 20 mins.
• Additional required assessment: one of Applied Mathematics and Scientific Computing, Operations Research and Optimization, Formal Mathematics and Theorem Proving, or Statistics (40 mins).