Data Scientist - Onshore (B)
This role focuses on building and deploying ML models and scalable data pipelines in Databricks to transform complex healthcare datasets, ensuring high-quality, trusted master data for member and provider analytics. The candidate will bridge data engineering and ML to resolve entity-resolution challenges while driving data-driven healthcare engagement solutions.
Skills required
About this role
V4C is seeking a Data Scientist with strong experience in Databricks, Python, machine learning, and Master Data Management (MDM) to help build data-driven solutions that support healthcare and member engagement initiatives. The ideal candidate will have experience working with large, complex healthcare datasets and transforming disparate data sources into reliable, analytics-ready data.
Key Responsibilities
- Develop and productionize machine learning models, statistical analyses, and predictive analytics using Python and Databricks.
- Build and maintain scalable data science workflows using Databricks, PySpark, SQL, Delta Lake, and related cloud data technologies.
- Work with MDM processes and frameworks to establish consistent, accurate, and trusted master data across multiple source systems.
- Analyze and resolve data quality, duplication, matching, and entity-resolution issues across member, provider, patient, and other healthcare-related datasets.
- Partner with Data Engineering, Product, Analytics, and business stakeholders to translate healthcare business problems into data science solutions.
- Develop data validation, profiling, and quality-monitoring approaches to improve reliability of analytical datasets.
- Perform exploratory data analysis and identify trends, patterns, and insights that can support member engagement and healthcare outcomes.
- Contribute to feature engineering, model evaluation, experimentation, and deployment of data science solutions into production.
- Ensure data solutions follow applicable healthcare data privacy, security, and governance requirements, including HIPAA where applicable.
- Document models, datasets, assumptions, methodologies, and data lineage to support reproducibility and governance.
Required Qualifications
- 8+ years of experience in Data Science, Machine Learning, Advanced Analytics, or a related field.
- Strong hands-on experience with Databricks and PySpark.
- Advanced Python and SQL skills.
- Experience developing and deploying machine learning or predictive models.
- Strong understanding of Master Data Management (MDM) concepts, including:
- Data matching and deduplication
- Entity resolution
- Golden/master records
- Data standardization
- Data quality
- Reference/master data
- Experience working with large-scale structured and semi-structured datasets.
- Experience with Delta Lake / Lakehouse architecture.
- Strong understanding of data governance, data quality, and data lineage.
- Experience working with healthcare, payer, provider, patient, or other regulated data is preferred.
- Experience working in a HIPAA-regulated environment is highly desirable.
Preferred Qualifications
- Experience with healthcare member/patient data and healthcare data models.
- Experience with MDM platforms such as Informatica MDM, Reltio, IBM MDM, or similar technologies.
- Experience with cloud platforms such as Azure or AWS.
- Experience with MLflow or similar model lifecycle management tools.
- Experience with Power BI, Tableau, or other analytics/visualization platforms.
- Experience building production-grade ML/data science pipelines.
- Familiarity with healthcare interoperability standards such as FHIR, HL7, or claims data is a plus.
Core Skills
Data Science: Python, Machine Learning, Statistics, Predictive Analytics
Databricks: Databricks, PySpark, Delta Lake, MLflow
Data: SQL, Data Quality, Data Governance, Data Lineage, Data Modeling
MDM: Master Data Management, Entity Resolution, Matching, Deduplication, Golden Records
Healthcare: Healthcare Data, HIPAA, Patient/Member Data, FHIR/HL7
Cloud: Azure/AWS
