Data Science Intern, Asset Intelligence

As a Data Science Intern for Asset Intelligence, you will learn and improve a service that normalizes, classifies, and enriches messy asset data for scientific instruments. You will trace the data pipeline, identify decision points, and own a specific improvement workstream focused on accuracy and data quality.

• Trace asset records through normalization, classification, and enrichment
• Reproduce the data pipeline and identify decision points
• Build and maintain a gold-standard reference set for classification accuracy
• Score match rate and classification accuracy by equipment class
• Cluster near-duplicate records and reconcile them as a group
• Analyze attribute coverage across the record base