Senior Business Intelligence Developer at Henry Ford Health (2026-02 – 2026-07)
Develop enterprise healthcare intelligence solutions by transforming Epic clinical, revenue cycle, and operational data into governed semantic models that support advanced analytics, predictive modeling, and AI-ready data products across regulated healthcare environments.
- Standardized clinical, financial, and operational data from Epic Clarity and Epic Caboodle into reusable semantic models using SQL Server, T-SQL, Power BI, and DAX, reducing dashboard refresh times by 35% while creating trusted data assets for enterprise analytics.
- Optimized revenue cycle datasets through dimensional modeling, SQL performance tuning, and Python automation, improving reimbursement reporting, denial analysis, and financial performance monitoring across healthcare operations.
- Designed governed analytical datasets supporting patient throughput, quality measures, CMS reporting, value based care, and executive decision making, enabling consistent downstream analytics and predictive modeling initiatives.
- Automated data validation, reconciliation, anomaly detection, and business rule enforcement using Python and SQL, improving production data quality and reducing manual verification across enterprise reporting pipelines.
- Strengthened enterprise data governance through HIPAA compliant access controls, PHI protection, Row Level Security, Azure DevOps release management, and version controlled deployments, ensuring secure delivery of analytical products across regulated healthcare environments.
Senior Data Engineer at Human Services Research Institute (2021-08 – 2025-04)
Designed and delivered enterprise healthcare data platforms supporting clinical analytics, claims processing, predictive modeling, and governed AI-ready data products across regulated healthcare environments.
- Healthcare data from more than 50 on-premises source systems lacked consistency for enterprise analytics; engineered scalable ingestion and transformation pipelines processing over 2M records monthly, reducing feature preparation time by 65% while improving downstream data reliability.
- Established a Medallion Lakehouse architecture with incremental processing and CDC, creating governed Bronze, Silver, and Gold data layers that improved data quality, lineage, and reuse across analytics and machine learning initiatives.
- Unified more than 12M Medicaid claims, provider, demographic, and operational records into standardized analytical datasets that enabled predictive models achieving 92% accuracy and supported healthcare funding decisions exceeding $2.5M.
- Replaced resource-intensive SQL workloads with distributed Spark processing, significantly improving scalability, execution efficiency, and reliability for enterprise healthcare data pipelines.
- Built reusable analytical datasets that became the foundation for clinical reporting, Revenue Cycle analytics, quality measures, HEDIS reporting, CMS reporting, and value based care initiatives across multiple business teams.
- Implemented automated validation, reconciliation, schema enforcement, and PHI quality checks, reducing manual verification effort by approximately 60% while strengthening trust in enterprise healthcare data.
- Introduced monitoring, automated alerting, SLA tracking, and root cause analysis to improve production stability, accelerate incident resolution, and strengthen operational reliability across critical data pipelines.
- Designed governed semantic datasets within Snowflake that enabled self-service analytics, standardized business definitions, and consistent reporting without duplicating transformation logic.
- Strengthened enterprise data governance by implementing HIPAA compliant access controls, PHI protection, data lineage, auditability, and Master Data Management practices across regulated healthcare datasets.
- Partnered with clinicians, analysts, product owners, and data scientists to translate healthcare challenges into scalable data products supporting predictive analytics and operational decision making.
- Mentored engineers on distributed data engineering, Spark optimization, code reviews, DevOps practices, and production support, improving engineering consistency and delivery quality across the team.
Data Science Intern at FEMA Research Project | George Mason University (2021-01 – 2021-05)
Applied machine learning, natural language processing, and graph analytics to convert unstructured emergency response data into operational intelligence.
- Reduced manual review by approximately 75% through a Python, TensorFlow, and spaCy NLP pipeline that classified more than 80K emergency requests for faster operational routing.
- Entity extraction and relationship mapping with spaCy, NetworkX, Python, and graph analytics surfaced patterns hidden in unstructured disaster records, improving situational analysis for emergency planning.
- Consistent experimentation required cleaner model inputs; automated preprocessing, feature engineering, and validation in Python, improving reproducibility and shortening machine learning iteration cycles.
Data Analyst at Accenture (2017-05 – 2019-07)
Established a foundation in enterprise analytics by converting operational data into repeatable reporting, validated datasets, and business ready insights.
- Automated recurring reporting with SQL, Python, Tableau, and SQL Server, reducing manual preparation by approximately 45% while expanding operational visibility across business functions.
- Production reports became more dependable after introducing SQL and Python reconciliation, cleansing, and business rule checks across large relational datasets.
- Reusable SQL models, dimensional structures, and Tableau data sources replaced inconsistent KPI calculations, improving reporting consistency for operational and executive teams.
- Translated changing business requirements into tested analytics releases through Agile, Jira, SQL, Python, and Tableau, coordinating with users, developers, and QA teams through deployment.
