Senior Data & AI Engineer

Hospice of the Valley is building analytics and AI solutions that support better care for patients and families. In this onsite role in Phoenix, AZ, you’ll help architect secure, scalable data platforms and production-grade machine learning pipelines using healthcare claims and clinical data.

What you’ll do

• Architect, implement, and optimize data solutions in Snowflake and Microsoft Fabric (including OneLake, Lakehouses, Warehouses, and Data Engineering pipelines).
• Develop robust ingestion frameworks for batch and streaming sources using tools such as ADLS, EventHub, APIs, and SFTP, with lineage and governance.
• Design conceptual/logical/physical models using approaches such as normalized, dimensional/star, and data vault where appropriate.
• Implement data mapping and transformations across structured datasets (claims, eligibility, provider, enrollment) and unstructured content (clinical notes, PDFs).
• Harmonize healthcare data using FHIR/HL7/CCDA, X12/EDI 837/835, NCPDP, and CMS standards, including record reconciliation and linking across EHR and HIE sources.
• Build ML pipelines for risk stratification, cost/utilization forecasting, fraud/waste/abuse detection, quality measure computation (for example, HEDIS), and care gap identification.
• Operationalize models with MLOps including experiment tracking, reproducibility, CI/CD, monitoring, and drift detection.
• Leverage LLMs/AI tools for data quality, entity resolution, summarization, and clinical insights while ensuring safety, bias checks, and auditability.
• Set up data cataloging, lineage, and metadata using Microsoft Purview or equivalent tooling.
• Establish quality SLAs, validation rules, profiling, and automated anomaly detection; instrument pipelines for cost, performance, and reliability (for example, Snowflake resource monitors and Fabric capacities).
• Partner with product owners, clinicians, actuaries, and analytics teams to translate requirements into scalable solutions.
• Deliver clear documentation such as data dictionaries and mapping specifications, and mentor engineers and analysts. Contribute to enterprise architectural roadmaps, reference patterns, and best practices.

What you bring

• 8+ years in data engineering/analytics and 5+ years hands-on with Snowflake (compute, storage, virtual warehouses, tasks, streams, Snowpipe, Time Travel, RBAC, row/column masking, data sharing, Dynamic Tables).
• 2+ years with Microsoft Fabric including OneLake, Lakehouses, Warehouses, Dataflows Gen2, Notebooks, and Pipelines, plus capacity management.
• Strong data modeling skills (dimensional/star, 3NF, data vault; surrogate keys, SCD types, conformed dimensions).
• Advanced SQL and proficiency with dbt or Fabric Dataflows/Power Query M, plus ADF/Synapse/Fabric Pipelines and Python for ETL/ELT.
• Experience mapping CMS datasets (claims/encounters, for example Medicare datasets), X12/EDI, FHIR/HL7, and provider/eligibility data.
• Comfort with structured (tables, CSV, Parquet) and unstructured data (clinical notes, PDFs, blobs), including optional NLP pipelines.
• ML experience with feature engineering, training/evaluation, deployment (for example scikit-learn, PyTorch/TensorFlow, Fabric ML or Notebook, Azure ML), and production monitoring.
• Security and compliance knowledge for HIPAA and PHI handling, auditing, data residency, BAAs, and practical access control in Snowflake/Fabric.
• Strong communication skills, including authoring mapping specifications and lineage documentation and presenting tradeoffs to technical and nontechnical stakeholders.

Benefits

• Supportive work environment with a culture of caring for patients and one another.
• Competitive wages and an excellent benefit program.
• Generous Paid Time Off.
• Flexible schedules to support work/life balance.