Senior Data Scientist

Job DetailsLevel: SeniorJob Location: Remote - Baltimore, MD 21244Education Level: 4 Year DegreeSalary Range: $170,000.00 - $205,000.00 Salary/yearPosition Overview a { text-decoration: none; color: #464feb; } tr th, tr td { border: 1px solid #e6e6e6; } tr th { background-color: #f5f5f5; } The Senior Data Scientist applies advanced analytics, statistical modeling, machine learning, and emerging artificial intelligence technologies to address complex healthcare and policy challenges. This role combines deep technical expertise with healthcare domain knowledge to transform complex data into actionable insights, support evidence-based decision-making, and drive innovation across Medicaid and CHIP programs. The Senior Data Scientist leads the development of analytical solutions, evaluates and implements advanced technologies including NLP and LLM/RAG frameworks, and collaborates with stakeholders to design scalable, data-driven products that improve program oversight, operational performance, and health outcomes. Responsibilities Formulate research, support development of solutions and recommendations for building value added products and solutions enhancing the current business operations and policy for Medicaid and CHIP programs. Lead evaluations of advanced technologies to identify best fits for business problems. Includes assessments of effectiveness, efficiency, security, cost, and other dimensions of candidate technologies. Design and lead implementation of natural language processing and LLM/RAG projects that allow users to derive insights from unstructured text data in multiple platforms. Perform routine business analysis and independent research using various techniques (e.g. statistical analysis, explanatory and predictive modeling, data mining), provide business data interpretation on Medicaid data sets to include beneficiary eligibility and enrollment, claims, expenditures, program oversight, scorecards, utilization metrics, performance data and more. Develop information and technical architecture, set up models, evaluate performance, modify parameters; help set technical standards. Work with variety of Stakeholders to identify analytical requirements and produce ad hoc data and reports that visualize data using industry best practices for HCD and UX. Qualifications a { text-decoration: none; color: #464feb; } tr th, tr td { border: 1px solid #e6e6e6; } tr th { background-color: #f5f5f5; } a { text-decoration: none; color: #464feb; } tr th, tr td { border: 1px solid #e6e6e6; } tr th { background-color: #f5f5f5; } U.S. Citizen or authorized to work in the United States and have resided in the U.S. for at least three of the past five years. Must be eligible to obtain a federal government client badge and successfully pass a Public Trust background investigation. Master's degree and a minimum of 10 years of professional experience, including at least 6 years of information technology experience, or an equivalent combination of education and experience. Four years of specialized experience may be substituted for a master's degree. Minimum of 4 years of experience conducting complex data analysis and applying data visualization techniques to support data-driven decision-making, program administration, policy development, program oversight, and continuous performance improvement initiatives. Demonstrated experience performing data analysis and research across Medicaid and CHIP domains, including Eligibility and Enrollment Performance Indicator data, T-MSIS Analytic Files (TAF), Behavioral Health, expenditures, Form CMS-416 reporting, and health outcomes analysis. Experience supporting the Centers for Medicare & Medicaid Services (CMS) or other federal or state government agencies is preferred. Expert-level proficiency in Python programming, including experience developing, reviewing, testing, and maintaining analytical code using commonly used data science, machine learning, and statistical libraries. Hands-on experience designing, developing, and implementing solutions utilizing Natural Language Processing (NLP), Large Language Models (LLMs), and Retrieval-Augmented Generation (RAG) technologies. Experience using source code management and DevOps tools, including GitHub and CI/CD platforms such as Jenkins, to manage code repositories, automated testing, and deployment pipelines. Subject matter expertise in text analytics, information extraction, document intelligence, and analysis of unstructured data. Strong foundation in statistical methods and analytical techniques, including probability distributions, hypothesis testing, regression analysis, predictive modeling, and other quantitative research methodologies. Excellent written, verbal, and presentation communication skills, with the ability to translate complex technical and analytical concepts for business, policy, and executive audiences. Experience developing interactive data visualizations and dashboards using tools such as Tableau, Power BI, AWS QuickSight, or similar platforms is preferred. Experience with enterprise knowledge management and search platforms such as Guru and Glean is preferred. Experience leveraging Databricks AI and machine learning capabilities, including generative AI offerings, is preferred.