Yale New Haven Health is looking for a Data Scientist to join our team. In this role, you will apply your analytic skills to understand forecasting challenges across the health system, propose pragmatic solutions, and develop applications that implement these solutions into daily operations. You'll need excellent technical abilities for manipulating large datasets and competency in using various mathematical, statistical, and machine learning approaches.

What You'll Do

Critically evaluate all requests for predictive applications.
Draft specification documents for new projects outlining needs, methods, timelines, and deliverables.
Review proposed development plans with JDAT leadership, evaluating project feasibility.
Design approaches to implement projects in daily operations.
Collaborate with other JDAT analysts to extract data for predictive projects.
Clean and validate data using exploratory analysis and input from customers and clinical experts.
Identify the best predictive analytics approach and algorithm(s) to address the needs.
Develop predictive applications and user interfaces for pilot testing.
Draft reports on application performance metrics for leadership and requestors.
Work closely with requestors to operationalize applications.
Develop final production applications and draft monitoring and maintenance plans.
Create user documentation for production applications.
Take ownership for production applications, working independently to ensure smooth operation.
Independently manage work effort across several deployed and in-production applications.
Deliver applications according to agreed-upon timelines.
Integrate with the analytics team, taking initiative to communicate and understand roles and processes.
Engage health system customers cordially and respond to requests promptly.
Take an active approach to ensure customer satisfaction, including proactive follow-up.
Maintain organized documentation on all predictive projects, from specification to maintenance.
Draft documentation for customers on application usage.
Document all project code thoroughly to ensure maintainability.
Use version control for all project code and documentation, keeping the central JDAT repository up-to-date.
Display strong organizational, problem-solving, and listening skills, with attention to detail.
Provide leadership and coordination to junior data scientists.
Provide training to other IT staff and user clients as appropriate.
Coordinate interactions and activities of vendors.
Regularly seek out other data science practitioners through online resources, local events, or conferences.
Learn from others' experiences, communicate new findings to the team, and attempt to use new techniques.
Pursue further career-related coursework, as approved by JDAT leadership.

What We're Looking For

Master's degree in data science, mathematics, statistics, engineering, or a closely related field.
Three years of experience in statistical analysis or related work.
At least one year of experience in health care analytics.
Experience programming with R to build machine learning models using techniques like GLMNet, random forest, and xgboost.
Ability to apply technical skills to business problems and deliver solutions.

Nice to Have

PhD preferred.
Epic certification in Analytics highly preferred.
Fluency with EHR tools for analytics, especially Epic Reporting Workbench, Caboodle and Clarity data models, Epic Cloud utilities, and Epic-provided predictive models.
Similar experience with Python preferred.
Experience building C and C++ routines that connect with R to optimize numerical routines is highly preferred.
Familiarity with low-level graphics libraries in R to develop novel data visualization methods.
Experience in applying abstraction and generalization to extract project features and communicate them simply to clinical or administrative staff.
Experience in communicating project outcomes to an academic audience.
Excellent written and oral communication skills.
Experience using the command-line interface in Windows and/or Linux.
Experience with open-source command-line utilities for data transformation and cleaning.
Experience using the git version control system.
Experience with good software engineering practices: writing discrete procedures, unit testing, and writing libraries or packages.
Ability to format written communications using the LaTeX document preparation system.

Technical Stack

Languages: R, Python, C, C++
Epic Tools: Reporting Workbench, Caboodle, Clarity, Epic Cloud
Algorithms/Libraries: GLMNet, Random Forest, XGBoost
Tools: Git, LaTeX

Team & Environment

This role is part of the JDAT (Joint Data Analytics Team) leadership structure and reports to JDAT leadership. You will collaborate closely with other analysts and team members.

Yale New Haven Health is an equal opportunity employer. We value integrity, a patient-centered approach, respect, accountability, and compassion.