Computational Structural Engineer & AI Benchmark Designer

Mercor; New York (NY); Hybrid; USD 110,000 - 170,000; Full time

Job summary

Mercor is building a large-scale benchmark to test AI systems on solving hard computational scientific problems. As a task designer, you’ll create challenging problems that require real scientific software to run simulations, interpret results, design experiments, and extract insights from data.

This role focuses on crafting original graduate-level problems based on real workflows, testing them with state-of-the-art AI models, and refining them until they achieve the desired difficulty.

Qualifications

• Graduate-level training in a STEM field (MS/PhD or equivalent)
• Proven proficiency with at least one listed scientific software/library
• Strong Python skills for problem setups, validators, and scripting
• Ability to design original, research-grade computational problems
• Independent work style and capability to refine designs from feedback
• Comfortable with Linux/terminal and remote compute sandboxes
• Available for 15–20 hours per week

Responsibilities

• Create graduate-level computational problems using specialized scientific software
• Design problems requiring multi-step workflows and strategic experiments
• Test problems against cutting-edge AI models and iterate to hit target difficulty
• Refine problems through a testing loop against model benchmarks
• Contribute to a library of benchmark problems and evaluation workflows

Skills

Python

Problem design

Analytical thinking

Linux/terminal

Education

MS/PhD in STEM

Tools

FEniCSx

OpenFOAM

deal.II

CalculiX

Elmer FEM

Code_Aster

SfePy

FiPy

Devito

Cantera

CoolProp

Pyomo

SimPy

scikit-fem

MFEM

Job description

Mercor is building a large-scale benchmark to test AI systems on solving hard computational scientific problems. As a task designer, you’ll create challenging problems that require real scientific software to run simulations, interpret results, design experiments, and extract insights from data.

This role focuses on crafting original graduate-level problems based on real workflows, testing them with state-of-the-art AI models, and refining them until they achieve the desired difficulty.