Healthcare Data Scientist (Medicare/Medicaid)

We are GDIT. We take pride in providing our clients with the data they need to make important decisions that impact the world around us.

You make GDIT your place by delivering insights to help our clients make impactful changes real. By owning your opportunity at GDIT, you’ll become a critical part in how we successfully solve our clients’ biggest challenges.

Our work is looking for a Data Scientist eager to grow their analytical and AI skillset while supporting vital efforts to detect and prevent fraud, waste, and abuse (FWA) in the Medicare and Medicaid programs. In this role, you will work alongside experienced data scientists and engineers, contributing to advanced analytics and generative‑AI initiatives.

Responsibilities:

• Supporting analytical tasks across data science, machine learning, and generative‑AI projects.
• Assisting with the analysis of Medicare and Medicaid claims data using statistical methods and supervised/unsupervised learning techniques.
• Helping develop components of generative‑AI solutions, including prompt pipelines, simple agents, embedding workflows, or retrieval‑augmented systems.
• Contributing to predictive modeling, anomaly detection, and other program‑integrity analytics.
• Building and maintaining clean datasets using Python and SQL-based tools.
• Creating clear visualizations to present trends, patterns, and model insights.
• Documenting work and communicating findings with team members and partners.
• Performing additional duties as assigned.

Required Skills:

• Bachelor’s degree with an analytical or technical focus (Statistics, Computer Science, Engineering, Applied Mathematics, etc.)
• At least 2 years of experience in Data Science
• Experience analyzing data, preferably healthcare or claims data
• Familiarity with Python or R for data analysis and machine learning
• Experience with common data science libraries such as Pandas, NumPy, Scikit-learn, Matplotlib, or Seaborn.
• Exposure to generative AI or modern machine learning frameworks (e.g., Hugging Face Transformers, LangChain, embeddings, vector databases)
• Familiarity with SQL and cloud data tools such as Databricks, Snowflake, or Spark is a plus.
• Understanding of basic statistics and foundational ML concepts such as feature engineering, train/test splits, and evaluation metrics.
• Ability to create and interpret data visualizations.