Data Scientist

Position Summary

Prometheus Federal Services (PFS) is a trusted partner of federal health agencies. We are exploring the addition of an experienced Data Scientist to support the Department of Veterans Affairs (VA) and federal health programs. The ideal candidate brings strong expertise in statistics, machine learning, and AI, along with hands-on experience using Databricks and cloud‑native analytics tools to develop scalable, high‑impact analytical solutions.

This role will support data-driven decision-making across federal health environments by developing predictive models, conducting advanced statistical analysis, and building reproducible analytical workflows. This role will collaborate with data engineers, analysts, clinicians, and program stakeholders to transform complex healthcare data into actionable insights that improve operations, outcomes, and mission performance.

• Apply advanced statistical methods (e.g., regression, time-series analysis, survival analysis, mixed models) to federal health datasets
• Conduct exploratory data analysis (EDA) to identify trends, anomalies, and actionable insights
• Develop, validate, and deploy machine learning and AI models for classification, prediction, clustering, and optimization
• Perform feature engineering, model evaluation, and interpretability analysis to ensure transparency and reliability
• Document analytical methods, assumptions, and results for technical and non‑technical audiences
• Build reproducible ML workflows using Databricks, MLflow, Azure
  
  ML services, implementing model monitoring, performance tracking, and retraining strategies
• Collaborate with engineering teams to orchestrate model deployment, monitoring, and integration
• Use Azure or AWS analytics services (e.g., Azure Data Factory, Synapse, Azure
  
  ML, S3, Glue, Sage Maker) to support scalable analytics and ML workloads
• Present analytical findings, model outputs, and recommendations to program leadership and stakeholders
• Document workflows, code, models, and analytical processes to support transparency and reproducibility
• Participate in Agile ceremonies and contribute to continuous improvement across data engineering, data science, and analytics product development

• Bachelor’s degree
• 4+ years of experience in data science, statistical analysis, or machine learning
• Strong proficiency in statistics, including hypothesis testing, modeling, and experimental design
• Hands-on experience with Databricks, Spark, and cloud-native analytics tools (Azure or AWS)
• Experience in Python, R, and SQL for data manipulation, modeling, and analysis, and Power BI or other visualization tools
• Experience developing data and analytics products in federal health environments, including working with clinical, operational, and financial data
• Authorized to work in the U.S. indefinitely without sponsorship
• Ability to obtain a public trust

• Master’s degree in a related field
• Experience developing and deploying machine learning models in production or environments
• Experience with MLOps practices (CI/CD, model monitoring, versioning)
• Knowledge of data governance, metadata management, or data quality frameworks