Databricks customers buy the platform; what they need is someone to make it work in their existing stack. I've spent four years at Tempus AI being that person inside a regulated environment — translating between business owners, scientists, and infrastructure teams.
Hand-picked because they map most directly to the work at Databricks.
Large-scale data analysis of 4+ million players' spatial navigation patterns to identify cognitive biomarkers for dementia research, processing 78,000+ complete game sessions.
Deep learning pipeline using DeepLabCut to track rat body parts and detect rearing behavior from video data, achieving high accuracy after 350,000+ training iterations.
End-to-end ML pipeline for security threat detection including data preprocessing, feature engineering, model training, and evaluation on real-world security datasets.
ML-based trading system using ensemble methods (BagLearner with Random Trees) to predict stock movements, with full backtesting simulation including transaction costs.
© 2026 Maxwell Vaglica. All rights reserved.