Mercy is seeking a Lead Data Scientist to work within a team of other advanced professional data scientists, engineers, and application developers in the generation, extraction, and compilation of data to perform creative, high-quality, state-of-the-art analyses and evaluations that produce insights, support decision-making, and drive impact within a leading and transforming healthcare organization. This position will support Mercys efforts to deliver on the vision of personalized, predictive, and proactive care. The candidate should demonstrate expertise with data extraction, management, analysis with data analytics tools, be able deliver outputs on a timeline, and lead others in the completion of related work. The candidate should be able to effectively document, develop, and communicate project plans and analytic findings with a variety of technical/non-technical stakeholders. This candidate will report directly to the Executive Director of Enterprise Data Science.
- Graduate degree in Public Health, Health Care Research, Epidemiology, Statistics, Data Science, Health Policy, Economic, Finance, Simulation/Simulation-Based Optimization, or related field.- At least 6 years of experience in a similar role in academia or industry or PhD + 3 years in a similar role in academia or industry- Have a strong knowledge of electronic medical record data, clinical data, claims data, or financial data.- Experience with SQL- Intermediate/Advanced development skills with at least one scripting language (Python, R, etc.) - Ability to quickly learn new analytic tools and packages- Ability to develop and apply computational algorithms and statistical methods to healthcare data (including, but not limited to data from electronic medical record, financial management, human resource, quality and supply chain)- Ability to develop and deploy healthcare-relevant predictive and prescriptive models.- Experience with Cloud-based data and AI solutions, especially in implementation and operationalization of Machine Learning based solutions.- Hands-on experience with a broad range of deep learning tools (e.g., TensorFlow, Spark, Theano, PyTorch, Scikit-learn, Keras, Caffe, Nvidia Digits) and collaboration environments (e.g. Jupyter notebooks, PyCharm, gitlab, github)- Excellent problem-solving skills- Strong organizational skills, an orientation toward detail, and collaboration oriented.- Present complex data (qualitative and quantitative) in a clear, concise, and compelling manner to both technical and non-technical audiences to inspire action.