Live opening · Posted 2 days ago
The key details from the original listing.
Live timing from JobBeeper.
Description supplied by the original job listing.
About Gramian
Gramian Consultancy is a boutique consultancy specializing in IT professional services and engineering talent solutions. With a strong background in software engineering and leadership, we help companies build high-performing teams by matching them with professionals who truly fit their needs.
About The Role
We are looking for a Mathematics expert with strong scientific programming skills to develop realistic, terminal-based computational tasks for an advanced AI benchmarking project.
You will translate authentic mathematical and research workflows into reproducible environments that evaluate whether AI agents can formulate mathematical problems, implement algorithms, debug numerical workflows, and produce verifiable computational results.
The role combines expertise in applied mathematics, numerical analysis, optimization, statistics, probability, and mathematical modeling with hands-on computational problem-solving and automated evaluation.
Core Domains
Applied Mathematics, Numerical Analysis, Optimization, Statistics, Probability, Mathematical Modeling, Differential Equations, Dynamical Systems, Operations Research, and Computational Geometry.
Key Responsibilities
Design authentic, multi-step computational mathematics tasks based on real-world research and mathematical workflows
Translate mathematical problems into self-contained, reproducible terminal environments
Prepare datasets, equations, model definitions, constraints, initial conditions, and expected outputs
Implement expert reference solutions using Python, R, Julia, C/C++, Bash, or other relevant tools
Develop tasks involving optimization, numerical integration, differential equations, matrix computation, statistical inference, stochastic modeling, and algorithm analysis
Define rigorous grading criteria covering numerical accuracy, convergence, complexity, feasibility, and mathematical correctness
Establish appropriate numerical 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 mathematical formulations, assumptions, expected outputs, and known limitations
Requirements
Advanced academic or professional expertise in Mathematics, Applied Mathematics, Statistics, Computational Mathematics, or a closely related quantitative discipline
Strong programming skills in Python, R, Julia, C/C++, Bash, or another relevant scientific programming language
Hands-on experience with numerical analysis, optimization, statistics, mathematical modeling, or computational mathematics
Experience implementing and validating mathematical algorithms or computational models
Ability to work independently in Linux or terminal-based environments
Strong understanding of numerical precision, convergence, stability, and mathematical correctness
Experience developing, debugging, and validating reproducible computational workflows
Work arrangement
Yes
Recently tracked roles with full details and direct application links.