Sr. Healthcare Data Scientist (Medicare/Medicaid)

GDIT is a technology and professional services company that provides data and technology solutions to government and other clients. The Senior Healthcare Data Scientist will develop advanced analytics and modern AI solutions to detect and prevent fraud, waste, and abuse in Medicare and Medicaid programs. The role involves analyzing claims data, building predictive and anomaly detection models, and presenting findings to technical, non-technical, and leadership audiences.

Responsibilities:

• Analyzing Medicare and Medicaid claims data using statistical and machine learning techniques
• Developing generative AI–powered solutions and agent-based systems to enhance fraud detection, investigate complex patterns, and optimize business processes
• Building predictive and anomaly detection models to improve insights, efficiencies, and program integrity outcomes
• Identifying opportunities to leverage large-scale CMS data with modern AI/ML methods, including LLMs, embeddings, vector databases, and retrieval-augmented pipelines
• Present findings to a range of audiences (technical/non-technical) and to various levels of leadership
• Performs additional duties as assigned

Requirements:

• Agentic AI, Big Data, Generative AI, Machine Learning Methods, Python (Programming Language)
• 5 + years of related experience
• No
• Bachelors degree with an analytical or technical focus (i.e., Statistics, Computer Engineering, Applied Mathematics) or related area
• Minimum 5 years of experience in Data Science
• Minimum of 2 years of experience conducting advanced analyses of Medicare and/or Medicaid data
• Familiarity with R or Python for data science (including machine learning)
• Familiarity and experience with one or more of the following data science packages: Pandas, NumPy, Tensorflow, Scikit learn, Seaborn, GGplot, Matplotlib
• Familiarity with SQL, Databricks, Snowflake and Spark languages/technologies
• Hands-on experience with generative AI technologies such as LangChain, LangGraph, Hugging Face Transformers, vector databases, agent frameworks, or LLM orchestration tools
• Understanding of statistics and basic analytic model development principles such as feature engineering, attribute selection, threshold setting, train/test split, etc
• Ability to create data visualizations to present complex analyses and to illustrate trends
• A self-starter mindset with strong curiosity, problem‑solving abilities, and the ability to simplify and explain complex data and AI systems
• 40
• Less than 10%
• Remote
• Any Location / Remote