Senior Analytics Engineer

The Senior Analytics Engineer transforms complex healthcare business needs into scalable, governed, and analytics-ready data solutions. This role is highly collaborative, requiring deep healthcare data expertise and the ability to design, develop, and iterate on high-quality analytics solutions that power insights and decision-making. This position works closely with clinical and operational stakeholders to develop trusted datasets, semantic models, and data products that enable reporting, advanced analytics, and measurable outcomes across the organization. The role emphasizes building sustainable data foundations, improving data quality, and enabling both productized insights and self-service analytics at scale., * Collaborate across clinical, operational, and business teams to deeply understand business processes and workflows, translating needs into scalable data models, curated datasets, standardized metrics, and AI-ready data assets that support analytics, machine learning, and decision-making

• Simplify and operationalize complex data and AI requirements by decomposing problems, identifying key assumptions, and designing maintainable, production-grade data and feature pipelines
• Design, build, and optimize data transformation pipelines and analytics models using cloud platforms (e.g., Azure Data Factory, Databricks, Microsoft Fabric)
• Develop and maintain feature engineering pipelines to support machine learning use cases (e.g., risk scoring, readmission prediction, utilization forecasting)
• Build reusable data marts and feature stores that serve both BI and AI/ML workloads
• Partner with data scientists and ML engineers to prepare high-quality, model-ready datasets and ensure consistency between training and inference data
• Help embed AI/ML outputs into clinical and operational workflows (e.g., alerts, prioritization queues, decision support tools)
• Develop and optimize semantic models, curated datasets, and dashboards in Databricks/Power BI/Tableau, ensuring alignment with standardized metrics and ML-derived insights
• Work hands-on with healthcare datasets, including claims, clinical, and operational data, ensuring correct interpretation for both analytics and ML use cases
• Ingest, transform, and normalize healthcare data using standards such as ICD-10, CPT, NDC, ensuring interoperability and consistency
• Employees will be required to perform other job-related assignments as requested

• Bachelor’s degree in information technology, Computer Science, or a related field, or equivalent experience
• 5+ years of experience working with healthcare data in analytics engineering, data engineering, or related data-focused roles, with increasing ownership of data modeling and analytics solutions
• Strong prior experience working with claims and clinical datasets across payer and/or provider environments, with the ability to translate data into actionable insights
• Prior experience designing and building scalable data models, curated data marts, and semantic layers to support BI and analytics use cases
• Deep understanding of healthcare data standards and vocabularies (e.g. ICD-10, CPT, SNOMED) and their application in analytics and interoperability use cases
• Experience with cloud data platforms (Azure preferred; AWS or GCP acceptable), including modern data stack components such as data lakes/lakehouses, distributed processing (e.g., Databricks/Spark), and orchestration tools
• Strong proficiency in SQL and experience with at least one programming language such as Python or Scala, with an emphasis on data transformation, validation, and performance optimization
• Familiarity with feature engineering and preparing ML-ready datasets, including assembling training datasets and supporting data pipelines for predictive use cases
• Demonstrated ability to move from ambiguity to clarity by translating business problems into structured data solutions, with a focus on scalability over one-off builds
• Experience in a healthcare services, payer, or provider organization
• Strong communication skills with the ability to translate complex technical concepts into business-friendly insights and influence both technical and non-technical stakeholders
• Hands-on experience with Databricks (Spark, notebooks, Delta Lake, workflows) preferred
• Knowledge of CI/CD, infrastructure-as-code, or data platform automation preferred

Preferred Knowledge, Skills and Experience

• Prior experience with healthcare integration engines like Rhapsody, Mirth etc.
• Prior experience with data governance, HIPAA compliance, and PHI handling

Paid orientation, License reimbursement, Paid training, Health insurance, 401(k) matching, Paid time off, Vision insurance, Dental insurance Full-time Remote in United States

Full job description

Overview: HarmonyCares is a leading national value-based provider of in-home primary care services for people with complex healthcare needs. Headquartered out of Troy, Michigan, HarmonyCares operates home-based primary care practices in 14 states. HarmonyCares employs more than 200+ primary care providers to deliver patient-centered care under an integrated, team-based, physician-driven model. Our Mission - To bring personalized, quality-based healthcare to the home of patients who have difficult accessing care. Our Shared Vision - Every patient deserves access to quality healthcare. Our Values - The way we care is our legacy. Every interaction counts. Go the extra mile. Empower and support each other. Why You Should Want to Work with Us

• Health, Dental, Vision, Disability & Life Insurance, and much more
• 401K Retirement Plan (with company match)
• Tuition, Professional License and Certification Reimbursement
• Paid Time Off, Holidays and Volunteer Time
• Paid Orientation and Training
• Great Place to Work Certified
• Established in 11 states
• Largest home-based primary care practice in the US for over 28 years, making a huge impact in healthcare today!

More details about the benefits we offer can be found at https://careers.harmonycares.com/benefits.