Math Expert with Ph.D

Role Overview

We are seeking Mathematics experts to develop realistic, terminal-based scientific tasks for Terminal Bench Science. You will design tasks involving numerical analysis, optimization, statistics, mathematical modeling, probability, dynamical systems, and computational mathematics.

The role focuses on evaluating whether AI agents can formulate mathematical problems, implement reliable algorithms, operate in a terminal environment, debug numerical workflows, and produce verifiable computational results.

Core Domains

Applied mathematics, numerical analysis, optimization, statistics, probability, mathematical modeling, differential equations, dynamical systems, operations research, and computational geometry.

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.

What we're looking for:

• 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.

Nice to have:

• 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.

Bonus Points

• 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.