2027 Internship Evaluation Engineer, Metric Prototyping
Core
Prototyping evaluation metrics and benchmarks to verify autonomous heavy construction equipment performance before training.
Role type
Intern, Metric Prototyping Engineer
Builds
Evaluation pipelines, benchmarks, and tooling for autonomous construction systems
Domain
Autonomous robotics, heavy construction equipment, geospatial data
Deliverable
production ML models
Required skills
Python, data pipeline construction, statistical intuition, metric formulation, field data collection, documentation
Preferred skills
ML evaluation frameworks, benchmarking methodology, geospatial data, point clouds, autonomous vehicle evaluation
Technologies
Python
Responsibilities
Partner with ML engineers to iterate on metric formulations; mine fleet datasets for reference examples and edge cases; observe machine performance at test sites; take physical ground-truth measurements; build evaluation tooling for performance regression triage; validate metric outputs against domain expert judgment; document metric definitions and failure modes
Seniority
Intern