Principal Data Architect (Data Science)

RESPONSIBILITIES
Data Ingestion: Design and build the pipelines that bring data in for feature engineering and machine learning. Feature Engineering: Use your knowledge of healthcare data, statistics, and data science to create features with real predictive power. Feature Extraction and Selection: Use techniques like clustering, text analytics, and PCA to find the most useful signals while preserving the meaning in the original data, so models stay accurate and scale well. Exploratory Data Analysis: Explore the data to find patterns, trends, and relationships, and use what you learn to match features with the right modeling approach. Model Development: Experiment with statistical and machine learning methods to build, tune, and optimize predictive models that fit the use case. Deployment: Ship production code that follows engineering best practices. Documentation and Communication: Document your work and share your approach, insights, and solutions with technical and non-technical audiences. Monitoring: Build and maintain the pipelines and processes that keep our enterprise data science products running smoothly. Quality and Integrity: Keep data and outputs accurate and reliable from start to finish. Collaboration: Partner with stakeholders, data scientists, data engineers, and product managers to build and deliver great data products.