Data Scientist Principal
Broadmoor Campus, United States
The University of Kansas Health System
Position Summary / Career Interest:
As a Data Scientist, you will discover and solve real world problems by analyzing clinical, operational, and financial data, defining new metrics and use cases, designing experiments, and creating models. All of this will be done as a part of the centralized Analytics and Business Intelligence department while collaborating with various stakeholders throughout the health system. This role explores and analyzes information to gain maximum insight that can give the organization a competitive advantage. The data scientist will need to be become a subject matter expert for the domains they support and the underlying data, including metadata and recommending ways to improve data quality. Further, the Data Scientist will be responsible for pioneering new methodologies, defining and improving performance metrics and evaluation, and will generally lead innovation efforts on the Data Science team.Successful candidates should have strong statistics background, programming skills, and understanding of the industry and how it operates. Critical thinking and problem-solving skills are essential for interpreting data, with good communication skills to deliver the findings. Candidates should be comfortable operating in a dynamic environment with ability to balance multiple priorities and competing deadlines. Lastly, the Data Scientist should have an entrepreneurial spirit, always asking "how can we do this better", to drive outcomes for patients as well as for the Health System as a whole.Responsibilities and Essential Job Functions
- Participate in all aspects of the project lifecycle from requirement gathering, hypothesis generation, data extraction and transformation, programming, testing, delivery of recommendations, implementation, and ongoing monitoring.
- Perform diagnostic analysis to drill down to the root-cause and isolate confounding information that creates a more complete understanding of current performance and informs ways to improve it.
- Develop robust models, using iterative model development process, based on statistical approaches and data mining techniques to provide insights and recommendations based on complex data sets that support and guide evidence-based practices.
- Formulate, train, and validate predictive models and algorithms to solve a diverse set of problems by incorporating latest research findings.
- Identify the most optimal modeling technique based on available data types and objectives/use cases (supervised, unsupervised, semi-supervised, or reinforcement learning).
- Implement efficient automated processes that produce modeling results at scale.
- Present stories told by data, that are actionable, in a visually appealing and easy to understand manner, to various levels of operations within the health system, including the executive team.
- Review tasks critically and ensure they are appropriately prioritized and sized for incremental delivery.
- Anticipate and communicate request and project roadblocks and delays before they require escalation.
- Must be able to perform the professional, clinical and or technical competencies of the assigned unit or department.
- These statements are intended to describe the essential functions of the job and are not intended to be an exhaustive list of all responsibilities. Skills and duties may vary dependent upon your department or unit. Other duties may be assigned as required.
Required Education and Experience
- Master's Degree in Computer Science, Mathematics, Statistics, Engineering, Economics, or another computational/quantitative field (or equivalent years in experience)
- 6 or more years experience using data mining/analytical methods and associated tools such as Python, R, etc.
- 6 or more years SQL experience in a relational database or an equivalent combination of education and experience
- 6 or more years experience working with various statistical methods, such as regression analysis, time series analysis, experimental design, etc.
- 1 or more years experience developing applications with one or more business intelligence tools such as Power BI, Qlik, SAP Business Objects, Tableau, etc.
Preferred Education and Experience
- Doctorate in Statistics, Epidemiology, Health Economics, Biostatistics, Computer Science, Clinical/Biomedical Informatics, or a related computational and quantitative discipline
- Experience with analytical documentation tools such as Jupyter Notebook
- Experience in healthcare environment
- Experience working with Caboodle
- Experience with one or more of the following data domains: Activity Based Costing, Hospital Industry Data Institute, Press Ganey, Vizient, Workday, etc.
Required Licensure and Certification
- Epic certification in 4 data model(s). If not certified, certification is required within 24 months from employment
Preferred Licensure and Certification
- Project Management Professional (PMP) - Project Management Institute (PMI) Project management, Lean, Six Sigma, Agile certification
- MS Certifications: Power BI Data Analyst Associate
Time Type:
Full timeJob Requisition ID:
R-41016We are an equal employment opportunity employer without regard to a person’s race, color, religion, sex (including pregnancy, gender identity and sexual orientation), national origin, ancestry, age (40 or older), disability, veteran status or genetic information.
Need help finding the right job?
We can recommend jobs specifically for you! Create a custom Job Alert by selecting criteria that suit your career interests.
* Salary range is an estimate based on our AI, ML, Data Science Salary Index 💰
Tags: Agile Biostatistics Business Intelligence Computer Science Data Mining Data quality Economics Engineering Jupyter Mathematics ML models Power BI Python Qlik R RDBMS Reinforcement Learning Research SQL Statistics Tableau Testing
Perks/benefits: Career development
More jobs like this
Explore more career opportunities
Find even more open roles below ordered by popularity of job title or skills/products/technologies used.