Design and execute evaluation protocols (datasets, metrics, statistical analysis) that reflect real user workflows for CAD/BIM and production conditions
Develop reproducible evaluation tools and automations to support model development, regression testing, and release-readiness decisions
Collect, process, and analyze data from multiple sources to assess model behavior and customer outcomes
Validate end-to-end ML-based product experiments and translate product requirements into measurable evaluation criteria
Communicate findings and recommendations clearly to researchers, engineers, product teams, and leadership
Document model quality issues discovered in production
Requirements
BS or MS in Mechanical Engineering, Architecture, Computer Engineering, Computer Science, Applied Mathematics, Statistics, or equivalent professional experience
4+ years of professional experience in ML model evaluation, ML QA, or applied ML engineering
Strong software engineering skills, including Python, data pipelines, testable and maintainable code, version control, and cloud-based workflows
Strong written communication skills to document evaluation methods, results, and recommendations