Architects, develops, and deploys high-performance machine learning systems across the full lifecycle. Responsibilities include large-scale feature engineering, online and offline pipelines, tree-based and deep learning models, low-latency serving, MLOps automation, model monitoring, and rigorous experimentation. The role requires production-grade software engineering, distributed computing, statistical expertise, and experience shipping ML systems in high-scale environments.

Build and maintain forecasting, driver-based models, and analytics for FP&A. Analyze historical and operational drivers, improve forecast accuracy with statistical and ML methods, create dashboards and automated reports, integrate ERP/CRM data, perform variance and scenario analysis, and present insights to finance leaders.

Lead design, build, and support of scalable data pipelines and integrations using Microsoft Fabric, ADF, PySpark, SQL, ADLS Gen2, and Databricks Unity Catalog. Drive Azure-to-Fabric migration, stabilize pipelines, tune performance, manage data governance, troubleshoot issues, document designs, mentor team members, and collaborate with stakeholders in Life Sciences regulatory environments during US Eastern hours.