Remote Senior Engineering Benchmark Designer

Weekday AI; United States; Remote; USD 17,000 - 23,000; Full time

Job summary

Weekday AI seeks an experienced Engineering Expert to design and validate complex engineering simulation problems for training AI models and coding agents. You will work across multiple engineering domains to create benchmarks with measurable objectives and verifiable outcomes.

The role requires a Master’s or PhD, 10+ years of hands-on design experience, and strong Python scripting. It is a remote, contractor-based engagement with ~40 hours/week and up to 24 weeks, overlapping PST.

Qualifications

• Master’s degree or PhD in Electrical, Mechanical, Aerospace Engineering, or closely related field.
• 10+ years of hands-on engineering design experience.
• Strong Python programming and scripting skills.
• Hands-on proficiency with at least one open-source simulation/design tool.

Responsibilities

• Design and develop self-contained engineering problems with clear requirements and optimization objectives.
• Build, configure, run, and validate simulation-based environments using open-source tools.
• Analyze AI execution logs to identify failures in reasoning and tool use.
• Calibrate task difficulty and refine benchmarks for objective grading.

Skills

Python programming

Analytical skills

Technical documentation

Independent work

Education

Master’s degree

PhD in Electrical/Mechanical/Aerospace Engineering

Tools

ngspice

PySpice

OpenFOAM

FEniCSx

CalculiX

python-control

OpenModelica

CadQuery

build123d

Cantera

Gmsh

Job description

Weekday AI seeks an experienced Engineering Expert to design and validate complex engineering simulation problems for training AI models and coding agents. You will work across multiple engineering domains to create benchmarks with measurable objectives and verifiable outcomes.

The role requires a Master’s or PhD, 10+ years of hands-on design experience, and strong Python scripting. It is a remote, contractor-based engagement with ~40 hours/week and up to 24 weeks, overlapping PST.