Computational Structural and Mechanical Engineer for AI Benchmark Design

Role Overview

Design original, graduate-level computational engineering challenges that evaluate whether advanced AI systems can perform research-level scientific work using real software. You will build and refine problems involving simulations, result interpretation, experiment design, and information discovery from data, with an emphasis on problems that reward rigorous reasoning rather than surface-level pattern matching.

Key Responsibilities

• Create computational problems requiring skilled use of specialized scientific and engineering software.
• Develop fully specified, multi-step problems with exact answers, as well as investigation-style problems where the system must strategically plan queries or experiments, interpret partial results, select measurements, and efficiently narrow possible solutions.
• Test each problem against advanced AI models and refine the design until it reaches the intended difficulty level.
• Write problem setups, oracle functions, and solution validators in Python.
• Design challenges based on real scientific workflows, including simulations, experimental design, and data analysis.

Technical Focus

Relevant expertise includes finite-element analysis, computational mechanics, structural analysis, elasticity, CFD, multiphysics simulation, heat and mass transfer, thermodynamics, combustion, fluid mechanics, HVAC and thermal systems, manufacturing simulation, optimization, and thermophysical-property calculations.

• Use open-source domain-specific tools such as FEniCSx/DOLFINx, scikit-fem, OpenFOAM, deal.II, MFEM, MOOSE, CalculiX, Elmer FEM, Code_Aster, SfePy, FiPy, Devito, Cantera, CoolProp, Pyomo, or SimPy.
• Apply knowledge of beam, plate, and shell analysis; linear and nonlinear elasticity; finite-element and variational formulations; mesh refinement and convergence studies; continuum and solid mechanics; coupled multiphysics; thermal-fluid simulation; structural or system optimization; reliability analysis; and related numerical workflows.
• Draw on relevant theory and numerical methods, including Euler-Bernoulli and Timoshenko beam theory, continuum mechanics, finite-element methods, Galerkin and variational methods, finite-volume methods, PDE discretization, constitutive modeling, thermodynamics, numerical linear algebra, and nonlinear solution methods.
• Experience with other open-source computational structural or mechanical engineering software, including scientific codes and solver frameworks built with Python, C, C++, or Fortran, is also relevant.

Qualifications

• Graduate-level training in a relevant STEM field, including an MS, PhD, or equivalent research experience. MS or PhD preferred.
• Proven hands-on proficiency with at least one listed scientific software library through research publications, open-source contributions, or professional work.
• Experience writing code with these libraries to solve real research problems, including an understanding of tool limitations, edge cases, and meaningful sources of problem difficulty.
• Strong Python skills.
• Ability to work independently and improve problem designs in response to feedback.
• Comfort working in a Linux terminal environment with remote compute sandboxes.

Preferred Qualifications

• Experience spanning multiple listed domains or tools.
• Familiarity with benchmark or evaluation design.
• A background in scientific teaching or designing exams and problem sets.
• Experience with computational reproducibility and containerized environments.

Work Terms

• Remote, hourly engagement.
• Availability of at least 15 to 20 hours per week is required.

Compensation

$70 to $85 per hour.