Senior Data Scientist: Statistical Modeling, AI/ML

Aptive Resources LLC is seeking an experienced and highly analytical Senior Data Scientist - Statistical Modeling, AI/ML, and Data Governance to support the Department of Veterans Affairs (VA) Electronic Health Record (EHR) program. This full-time role will support advanced statistical modeling, machine learning and AI evaluation, data governance, data quality assurance, operational analytics, and executive decision support for complex VA healthcare and EHR modernization efforts.

This is a hands-on senior data science position, ideal for someone who combines deep theoretical statistical and mathematical expertise with practical experience improving healthcare data operations. The ideal candidate can evaluate when statistical, AI, or machine learning approaches are appropriate, diagnose when models or reports are not performing as expected, identify data quality and process problems, and build reproducible analytics products using R, SQL, Python, Git, GitHub, and modern cloud/data platforms.

• Lead statistical modeling, AI/ML evaluation, and analytic decision support for VA EHR modernization, operational reporting, and executive-facing analytics workstreams.
• Design, evaluate, and explain statistical and machine learning models, including distributional assumptions, matrix-based methods, dimension reduction, clustering, NLP, simulation, time-series modeling, Bayesian methods, and model limitations.
• Assess model quality, reliability, bias, drift, and operational usefulness; identify when an analytical approach is not statistically valid or is not appropriate for the available data.
• Serve as a data governance and data quality assurance point of contact, proactively identifying defects, gaps, anomalies, reporting inconsistencies, data capture issues, and root causes across complex datasets and reporting processes.
• Develop, maintain, and document reproducible R-based analytics, R packages, scripts, pipelines, dashboards, and governed reporting outputs.
• Integrate and validate data from enterprise healthcare, operational, EHR, ServiceNow, Corporate Data Warehouse (CDW), Databricks/Azure, and other data sources to support reliable program reporting.
• Translate stakeholder questions into actionable metrics, KPI definitions, data validation rules, dashboard requirements, quality checks, and recurring reporting products for PMO, functional, and executive audiences.
• Advise on data governance, provenance, metadata, versioning, access control, code review, documentation, and production standards for analytics teams.
• Use Git/GitHub and documentation workflows to support version control, collaborative development, pull requests, code review, reproducibility, and transparent analytical delivery.
• Partner with analysts, data engineers, program managers, and VA stakeholders to move ad hoc analyses into governed, repeatable, auditable data products and reporting processes.
• Support Agile/SAFe delivery by helping define features, user stories, acceptance criteria, sprint-ready analytics work, and backlog priorities.

• 5+ years of applied data science, statistics, machine learning, health informatics, data engineering, or analytics experience in complex enterprise or healthcare environments; federal health, VA, or VHA experience strongly preferred.
• Advanced degree or equivalent experience in statistics, biostatistics, mathematics, data science, computer science, public health, health informatics, or a related quantitative field.
• Strong theoretical and applied statistics foundation, including statistical distributions, mathematical modeling, matrix/linear algebra concepts, inference, uncertainty, and model diagnostics.
• Demonstrated AI/ML experience with the ability to evaluate when models are appropriate and reliable, and to diagnose conditions under which models underperform, drift, become biased, or fail.
• Advanced proficiency in R for statistical computing, modeling, reproducible analytics, and package/tool development; experience developing or maintaining R packages is strongly valued.
• Strong SQL skills for querying, joining, validating, and transforming large datasets; working knowledge of Python preferred.
• Hands-on experience with Git and GitHub for version control, collaboration, code review, and reproducible delivery.
• Experience supporting data governance, data quality assurance, stewardship, metadata, lineage, provenance, versioning, access control, and analytics documentation.
• Excellent communication and documentation skills. Able to brief executives, translate technical findings into operational implications, and guide teams toward clean, auditable, compliant analytics.
• U.S. Citizenship and ability to obtain a Public Trust clearance.

• Direct experience supporting VA, VHA, VA OIT, Federal EHR modernization, Oracle Cerner/VistA/CPRS transition, or VA enterprise reporting.
• Experience with Databricks, Azure, Delta tables, Medallion architecture, ServiceNow, Power BI, SAS, Jira, and Confluence.
• Experience developing executive operational reporting, go-live readiness reporting, issue/configuration tracking, SLA/throughput metrics, or command center decision support.
• Experience with NLP, document-term matrices, TF-IDF, topic modeling, BERTopic, RAG, prompt engineering, LLM/AI agent evaluation, or knowledge management analytics.
• Experience creating open-source or internal R packages, style guides, code review frameworks, reusable analytics standards, or production documentation for analytics teams.
• Ability to work in high-pressure, delivery-critical environments with shifting priorities, ambiguous data, and multiple dependencies.