Sean Wade

• Architected data schema and privacy preserving data collection framework for launch of multiple health related programs (Lumihealth, Heartline, Attain)
• Led cross-functional team in developing, shipping and maintaining core on-device ML algorithms to 200k+ users:
• Personalized exercise plan recommender system
• Unsupervised walk detection algorithm
• Contextual notification engine using routine identification (commute to work, typical workout time, etc)
• Meal logging tool with food image classification
• Evaluated performance of ML models and features by defining metrics, causal inference analysis on user behavior and designing effective experiments
• Built data pipelines to process petabytes of complex data (Apple Watch sensors, app logs, medical claims)
• Created dashboards and alerting to monitor KPIs and releases

• Created tools to improve deploying, evaluating, and retraining ML models on Azure
• Extended Azure SDK to incorporate open source projects like MLflow

• Developed recommender system for rides/attractions in Disney World Park app
• Created realtime pipelines and dashboards to monitor performance

• Used drone imaging and photogametry to construct 3D models of buildings
• Built convolutional neural network to identify and classify roof damage

Researched synthetic cancer cell image generation using conditional adversarial neural networks and wrote a python library to distribute it. Created novel methods for representing medical claims history with vector embeddings.