We are seeking an experienced AI Data Integration Engineer with strong hands-on expertise in Snowflake, healthcare claims data, and AI/LLM integration. The role will build secure, sanitized healthcare data layers and pipelines that enable AI systems to generate insights, identify patterns, optimize costs, and support business decisions.
The ideal candidate will combine data engineering, AI/LLM development, and healthcare domain expertise, with experience integrating AI solutions using Azure OpenAI and/or Azure AI Foundry.
Responsibilities
- Design and develop secure Snowflake views, data models, and ETL/ELT pipelines for healthcare claims data.
- Build sanitized data layers using SQL, JSON, UDFs, secure views, and masking policies.
- Integrate structured healthcare data with LLMs, APIs, and AI workflows.
- Develop prompt pipelines and AI-driven analytics using Azure OpenAI, OpenAI, or Anthropic.
- Apply HIPAA, PHI minimization, and healthcare data de-identification practices.
- Collaborate with product, clinical, actuarial, analytics, and engineering teams to translate requirements into scalable solutions.
- Develop AI use cases such as cost-driver analysis, utilization trends, adherence insights, and savings opportunities.
- Optimize Snowflake performance, data quality, security, and scalability.
- Document solutions and build reproducible, maintainable data and AI pipelines.
Required Skills
- 3+ years of hands-on Snowflake experience
- Strong SQL, Python, JSON, UDFs, secure views, masking policies, and data modeling
- Experience building ETL/ELT pipelines using tools such as dbt, Matillion, or Airflow
- 1–2+ years of applied AI/LLM development
- Experience with LLM APIs, prompt engineering, and integrating structured data into AI workflows
- Experience working with healthcare claims data, preferably medical or pharmacy claims
- Strong understanding of HIPAA, PHI, data privacy, and de-identification
- Experience with APIs, Git, and modern data engineering practices
Preferred Skills
- Azure AI Foundry – models, deployments, agents, tool calling, and retrieval
- Azure OpenAI in healthcare/HIPAA environments
- RAG, embeddings, vector databases, and semantic search
- Azure Functions, Service Bus, Microsoft Fabric, FHIR APIs
- Databricks and healthcare data platforms
- PBM/payer experience and pharmacy claims
- AI copilots, automated insights, or AI-driven analytics
- MLOps, data governance, and privacy engineering
Success Criteria
- Secure and validated Snowflake healthcare data layer successfully deployed.
- Reliable AI/LLM integration producing accurate and explainable insights.
- Reduced manual analytics effort through automation.
- Reproducible, well-documented data and AI pipelines.
- Successful AI prototype/pilot using Azure AI Foundry.
- Effective collaboration with product, clinical, analytics, and engineering teams.