LLM Engineering Expert- Simulation & Design
Core
Author and validate complex, multi-constraint engineering design problems (model-breaking tasks) to train and evaluate state-of-the-art AI agents in domains like Electrical, Mechanical, and Aerospace engineering.
Role type
Senior IC LLM Engineering Expert (Simulation & Design)
Builds
Automated, objective graders and benchmark datasets for AI agent evaluation
Domain
Engineering simulation (Electrical, Mechanical, Aerospace, Robotics) + AI Evaluation
Deliverable
production ML models | product features
Required skills
Engineering design (10+ years), Python scripting, open-source simulation tools (ngspice, PySpice, OpenFOAM, etc.), LLM evaluation concepts (pass@k, failure-mode analysis), trajectory log analysis, autograder development
Preferred skills
Weekend on-call availability, experience in AI evaluation or data annotation
Technologies
ngspice, PySpice, OpenFOAM, FEniCSx, CalculiX, python-control, CadQuery, build123d, OpenModelica, Cantera, Gmsh
Responsibilities
Author original engineering design tasks with competing constraints and validated reference solutions; Build and validate problem environments using simulation tools and Python test benches; Evaluate coding agent outputs and execution logs to identify systemic failure modes; Iteratively refine problem difficulty based on empirical model performance data; Partner with AI researchers and domain experts to integrate benchmarks into evaluation pipelines
Seniority
Senior, hands-on IC
