AI Data Engineer

SUMMARY: The AI Data Engineer is a hands-on technical expert who builds the data foundation and AI-driven applications that help InterMed automate work and make better decisions. The role develops custom applications and AI agents that automate business and clinical workflows end to end, creatively leverages EMR and other healthcare data, and helps the Business Intelligence (BI) team grow its Python and AI-assisted development skills. It also builds and optimizes InterMed’s cloud data platform on Microsoft Fabric and Power BI, including the semantic models that power AI-assisted reporting and self-service, while supporting the existing SQL environment as workloads move to Fabric. The ideal candidate combines strong data engineering fundamentals with hands-on experience in LLM and AI tooling and is excited to leverage AI capabilities to reshape data strategy  

• →Data Platform 
  • →Assist with the migration of BI workloads from the on-premises SQL and SSIS environment to Microsoft Fabric; assess which legacy packages to retire, rebuild, or re-architect, and maintain existing SQL Server, SSMS-based workflows, and SSIS packages to ensure continuity of reporting during the transition 
  • →Design and build data pipelines into Fabric OneLake from source systems (for example, eClinicalWorks, payer and ACO files etc.), including orchestration, scheduling, dependency management, alerting, and failure recovery 
  • →Complete the data warehouse build-out across priority subject areas, applying a SQL-based transformation framework (for example, dbt) for modular, tested, version-controlled, and documented data models 
  • →Build and publish certified Power BI semantic models with governed measures, definitions, and business-friendly descriptions that power Copilot report building and self-service data agents, and support the transition of reporting from Tableau to Power BI 
  • →Build and maintain Python automation scripts and APIs that support data pipelines, applications, and agents 
  • →Ensure strong data quality, integrity, and security controls across the platform, including HIPAA and PHI safeguards and automated monitoring and alerting on key data quality metrics 
• →AI Use & Development  
  • →Evaluate and integrate LLM-powered tooling (for example, Claude, Copilot, or equivalent) to accelerate data workflows and enable natural-language data access 
  • →Establish team standards for responsible AI-assisted development, including use of AI tools to write, review, test, and document code and queries, with human review of generated output 
  • →Use AI to optimize dashboard builds and capabilities for end user agents and self-service analytics 
  • →Design, build, and deploy purpose-built applications and AI agents that automate BI, IT, other administrative and clinical workflows end to end, from data intake through action and audit trail 
  • →Develop custom apps and agents using low-code tools within the Microsoft ecosystem (for example, Power Apps, Power Automate, and Fabric data agents) and Python- and LLM-based custom agents for multi-step workflows where low-code tools fall short 
  • →Creatively leverage EMR and other data sources, including structured fields, clinical documentation, and other unstructured sources, to support new analytics, automation, and clinical and operational use cases, in compliance with HIPAA and PHI safeguards 
  • →Partner with IT on the integration, deployment, and ongoing operation of applications and agents 
  • →Serve as an advisor to IT and business partners on AI vendor point solutions: assessing fit, overlap with in-house capabilities, data access and integration requirements, and build-versus-buy tradeoffs 
  • →Develop analyst capability in Python, flexible coding, unstructured data techniques, and AI-assisted development through coaching, code review, and shared patterns and templates 
  • →Maintains strict confidentiality in alignment with HIPAA (Health Insurance Portability and Accountability) guidelines and InterMed policies. 
  • →Perform other duties to support the mission, vision and values of InterMed. 

• Follows InterMed’s mission to provide patient-centered primary care, putting the patient first to deliver high quality, high value care. 
• Provide the highest quality care to our patients with a level of service that exceeds their expectations. 
• Maintain a positive attitude and always treat our patients and each other with dignity and respect. 
• Insist on honesty and integrity from each other and our business partners. 
• Make teamwork a core component of our relationships between physicians, colleagues, and patients. 
• Embrace change to better serve our patients. 
• Use business practices that feature individual accountability and group responsibility to ensure delivery of high value healthcare. 
• Have fun as we carry out our mission to serve.  

• Python or equivalent for data engineering: writing modular, testable pipeline code, custom operators, and data quality scripts 
• Proficient SQL and strong data modeling expertise, including dimensional modeling, star schema design, and performance optimization — with hands-on experience in SQL Server environments 
• Uses AI coding assistants and LLM-powered tools as part of everyday work to accelerate data engineering, analysis, and documentation; applies judgment, reviews AI-generated output, and understands AI’s limitations 
• Experience designing Power BI semantic models, including relationships, governed measures, and descriptions that support accurate AI-generated reports and answers 
• Deep knowledge of modern data architecture patterns (for example, lakehouse, medallion, or cloud ELT) and the ability to map a path from legacy on-premises environments to those patterns 
• Hands-on experience with a SQL-based transformation framework (for example, dbt) and a pipeline orchestration tool 
• Experience building applications or AI agents that automate multi-step workflows, using low-code platforms (for example, Power Apps and Power Automate) and/or Python with LLM APIs and agent frameworks 
• Ability to work with unstructured and semi-structured data (for example, clinical notes, documents, and JSON) in addition to relational data 
• Ability to coach analysts with varied technical backgrounds and raise team coding standards 
• Familiarity with Microsoft Fabric and Power BI and how they fit within a broader Microsoft environment (Azure, M365, Microsoft Entra ID) preferred 
• Experience in healthcare, health tech, or regulated environments; HIPAA/PHI familiarity a plus 
• Strong analytical reasoning and problem-solving skills; able to operate effectively in ambiguous environments and lead through uncertainty 
• Clear communication skills with the ability to explain technical concepts, architecture tradeoffs, and migration plans to non-technical audiences and leadership 

• Education: 
  • Bachelor’s degree in Computer Science, Information Systems, or a related field; or equivalent combination of education and experience 
• Experience: 
  • 3-5 years of hands-on experience with AI, data engineering, BI development, or data architecture, with demonstrated ownership of production pipelines and infrastructure 
  • Proficiency in Python for data engineering: transformation, automation, pipeline development and data quality scripts 
  • Advanced SQL skills with hands-on experience in SQL Server and SSMS-based environments preferred 
  • Hands-on, daily experience using AI coding assistants and AI tools (for example, Claude Code, GitHub Copilot, or similar) to write, test, debug, and document code and queries 
  • Familiarity with Microsoft Fabric, Azure data services, Snowflake or a comparable cloud data platform, and how it integrates within a broader Microsoft technology environment 
  • Deep understanding of data engineering, analytics, and end-to-end data workflows from source system to consumption layer 
  • Demonstrated experience delivering at least one production application, automation, or AI agent that replaced a manual business process 
  • Experience with version control, CI/CD workflows, and code review practices for data assets 
  • Demonstrated ability to design, document, and govern enterprise data models and architecture