AI Data Engineer — Build HIPAA‑Compliant AI Pipelines

InterMed, P.A.; South Portland (ME); On-site; USD 105,000 - 153,000; Full time

Job summary

InterMed, P.A. in South Portland, ME seeks an AI Data Engineer to build an AI-ready data foundation, driving automated clinical and business workflows.

You will modernize data platforms with Microsoft Fabric and Power BI, and develop LLM-enabled tooling while safeguarding HIPAA/PHI protections. This role spans data engineering, analytics enablement, and governed AI development, including migrating BI workloads, designing Fabric OneLake pipelines, and delivering reusable pipelines, semantic

Qualifications

• Bachelor's degree in Computer Science, Information Systems, or a related field, or equivalent combination of education and experience.
• 3-5 years of hands-on experience with AI, data engineering, BI development, or data architecture, with proven ownership of production pipelines.
• Proficiency in Python for data engineering tasks including transformation, automation, and pipeline development.
• 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 to write, test, debug, and document code and queries.
• Familiarity with Microsoft Fabric, Azure data services, Snowflake or equivalent cloud data platform and how it integrates in a Microsoft environment.
• Deep understanding of end-to-end data workflows from source to consumption.
• Proven experience delivering at least one production application, automation, or AI agent that replaced a manual process.
• Experience with version control, CI/CD workflows, and code review practices for data assets.
• Ability to design, document, and govern enterprise data models and architecture.

Responsibilities

• Migrate BI workloads from on-premises SQL and SSIS to Microsoft Fabric, assessing which legacy packages to retire, rebuild, or re-architect while maintaining reporting continuity during the transition.
• Design and build data pipelines into Fabric OneLake from source systems (eClinicalWorks, payer and ACO files) including orchestration, scheduling, dependency management, alerting, and failure recovery.
• Deliver data warehouse build-out across priority subject areas using a SQL-based transformation framework (e.g., dbt) with modular, tested, version-controlled, and documented data models.
• Build and publish certified Power BI semantic models with governed measures and descriptions powering Copilot report building and self-service data agents; support transitioning reporting from Tableau to Power BI.
• Create and maintain Python automation scripts and APIs that support pipelines, applications, and agents.
• Maintain data quality, integrity, and security controls, including HIPAA/PHI safeguards and automated monitoring for key data quality metrics.
• Evaluate and integrate LLM-powered tooling to accelerate data workflows and enable natural-language data access.
• Establish team standards for responsible AI development, including AI-assisted coding with human review of generated output.
• Use AI to optimize dashboard builds and capabilities for end-user agents and self-service analytics.
• Develop custom apps and agents using Power Apps, Power Automate, Fabric data agents, and Python- and LLM-based agents for multi-step workflows.

Skills

Python for data engineering

SQL

AI tooling

Version control

CI/CD

Data modeling

Education

Bachelor's degree in Computer Science or Information Systems

Tools

Python

SQL Server

SSMS

SSIS

Fabric OneLake

Power BI

dbt

GitHub Copilot

Claude Code

Power Apps

Power Automate

LLM APIs

EMR

Job description

InterMed, P.A. in South Portland, ME seeks an AI Data Engineer to build an AI-ready data foundation, driving automated clinical and business workflows.

You will modernize data platforms with Microsoft Fabric and Power BI, and develop LLM-enabled tooling while safeguarding HIPAA/PHI protections. This role spans data engineering, analytics enablement, and governed AI development, including migrating BI workloads, designing Fabric OneLake pipelines, and delivering reusable pipelines, semantic