AI Data Engineer

POSITION SUMMARY: Our client is building an AI-first data platform designed to support advanced analytics, automation, and AI-driven applications across the organization. The AI Data Engineer will own and build the underlying data infrastructure that makes this possible. This is a hands-on, individual contributor role responsible for data pipelines, lakehouse architecture, governed datasets, and the data products that support AI and analytics. You will work at the intersection of modern data engineering and AI delivery, using tools such as Claude Code to accelerate development while maintaining strong standards for architecture, security, quality, and governance. The ideal candidate is someone who views data infrastructure as a product—not simply a collection of pipelines—and takes ownership of reliability, scalability, data quality, and the experience of downstream consumers. RESPONSIBILITIESOwn the Data Platform Own Bronze / Silver / Gold data pipelines using Microsoft Fabric and OneLakeDesign and maintain governed semantic layers supporting Power BI and downstream analytics Ingest data from multiple source systems into Microsoft Fabric and Azure SQL with appropriate quality, security, and lineage controls Implement data governance, security, and PII handling practices aligned with Entra IDExpose curated datasets to AI agents through approved APIs, MCP servers, or similar interfaces Use Claude Code and other AI coding tools to accelerate development while reviewing and validating all AI-generated code before production deployment Orchestrate, monitor, troubleshoot, and optimize pipelines for reliability, performance, and cost Manage Git-based version control and deployment pipelines across development, test, and production environments Support Reporting and Data Requests Support ad-hoc requests across Microsoft Fabric and Power BI, including report, dataset, and data-quality enhancements Build and maintain paginated and operational reports Write, debug, and optimize SQL for reporting, investigation, and troubleshooting Use AI coding tools to investigate and diagnose platform, data-quality, and reporting issues Support and optimize Power BI semantic models and DAX for downstream consumersREQUIREMENTSRequiredHands-on experience building and maintaining data pipelines in Microsoft Fabric, including Lakehouse architecture and OneLakeStrong understanding of Bronze / Silver / Gold medallion architecture and semantic-layer modeling Experience with Azure SQL, ADLS Gen2, and data ingestion across multiple source systems Understanding of data governance, security, and PII handling, including Entra IDExperience exposing data products through APIs, MCP-style interfaces, or similar mechanisms for AI and analytics consumption Current, hands-on use of AI coding tools such as Claude Code as part of your development workflow Strong SQL and data-engineering fundamentalsUS Citizenship required; no sponsorship or green card holders due to confidential data requirements Strongly Preferred Experience building data infrastructure supporting AI agents, machine learning models, or agentic workflows Experience with Power BI and Direct Lake Experience working within structured engineering standards, documentation-first workflows, and formal code-review processes Exposure to MCP (Model Context Protocol) servers or similar AI data-access patternsNOT REQUIREDPeople management experience — this is an individual contributor role Industry-specific domain expertise — the ability to learn the business and apply strong data-engineering fundamentals is more importantWHO THRIVES IN THIS ROLEThis role is a strong fit for someone who takes genuine ownership of data infrastructure. You don't just build pipelines when a ticket arrives—you think about the platform as a product with real users and downstream consumers. You are already using AI tools to improve how you design, develop, troubleshoot, and ship software. You care deeply about data quality, governance, and reliability, while still moving quickly. You are excited by the opportunity to build modern data infrastructure that directly enables AI, analytics, and automation rather than maintaining a legacy environment. If you're a hands-on data engineer who wants to play a meaningful role in building an AI-first data platform, this role offers the opportunity to have significant ownership and impact.