Data Scientist at Merative in Ann Arbor, Michigan

Job Description:

Data Scientist, Merative US LP, Ann Arbor, MI and various unanticipated client sites throughout the US (100% telecommuting permitted): Develop healthcare models using state-of-the-art machine learning algorithms, including libraries such as scikit-learn, SHapley Additive exPlanations (SHAP), TensorFlow or MLlib. Collect and analyze information such as medical records or billing information to extract useful and actionable insights to inform clients of problems. Create documents as needed to support and perform communications with internal and external clients, including dashboards, presentations, or methodology documentation. Explain the findings to non-experts so they can understand and use the high-level methodologies. Provide input to stakeholders based on business use cases to make decisions when multiple approaches are possible. Work on planning, designing, implementation, testing, deployment, and day-to-day operation of entire research and software development cycle. Design, write, test, debug, and deploy high-quality software to implement the statistical methodologies and machine learning models for various healthcare datasets. Perform adjustments to the standard technique so that refinements and new methodologies are developed with results compared to traditional approaches. Develop expertise with existing methodologies to architect, design and implement new functionality and product enhancements. Develop algorithms and production level code with scalable software systems that run on cloud platforms as well as on-prem solutions. Utilize: Python, PySpark, Statistical Analysis System (SAS), Machine Learning (scikitlearn, SHAP, MLlib), Deep Learning (TensorFlow), MapReduce, Hadoop, Hive, GitHub, Jira. Required: Master’s degree or equivalent in Computer Science, Engineering, Information Technology, Mathematics, Statistics or related (employer will accept a Bachelor's degree plus five (5) years of progressive experience in lieu of a Master’s degree) and one (1) year of experience as a Data Scientist or related. One (1) year of experience must include utilizing Python, Pyspark, Statistical Analysis System (SAS), Machine Learning (scikit-learn, SHAP, MLlib), Deep Learning (TensorFlow), MapReduce, Hadoop, Hive, GitHub, Jira. Please send resumes to recruitad@us.ibm.com. Applicants must reference D143 in the subject line.