Contract AI Data Engineer

Founded in 1989 and headquartered in Chicago, Jet Support Services, Inc. (JSSI) is the largest independent provider of hourly cost maintenance programs for business aviation. JSSI delivers comprehensive coverage for engines, airframes, and auxiliary power units (APUs) across more than 300 different aircraft makes and models, helping owners and operators stabilize maintenance budgets, maximize aircraft availability, and protect asset value throughout the lifecycle of ownership. JSSI has built a portfolio of complementary business lines designed to simplify the economic and technical complexity of business aviation; these include Maintenance teams, Traxxall maintenance tracking software, Parts & Engines, Conklin aircraft cost and performance data, and Aviation Capital asset-based financing solutions. Together, these offerings support owners, operators, and maintenance providers with integrated tools spanning ownership and maintenance planning, execution, and financial management. With more than 6,500 aircraft supported through programs and software platforms, JSSI leverages its unique independence, unmatched scale, and data-driven insight to deliver customized solutions and support models aligned to the interests of each client — regardless of aircraft platform. JSSI is backed by leading institutional investors GTCR, Genstar Capital, and Blackstone. Learn more at jetsupport.com.

JSSI is building an AI-first data platform, and the AI Data Engineer is the person who builds and owns it. You are the platform owner — responsible for the pipelines, the lakehouse, and the governed datasets that make AI and analytics possible across every JSSI business unit.

This is a hands-on, individual contributor role. You will design and build the data infrastructure that AI agents depend on, ensure data quality and governance are production-grade, and work at the intersection of data engineering and AI delivery. You will use Claude Code to build pipelines against JSSI standards and be a core part of how the organization accelerates.

Own the data platform

Own Bronze / Silver / Gold pipelines in Microsoft Fabric and OneLake

Model governed semantic layers; serve Power BI via Direct Lake

Ingest business-unit data into Azure SQL and ADLS Gen2 with quality and lineage controls

Enforce data governance, security, and PII handling aligned to Entra ID

Expose curated datasets to AI agents through approved MCP servers only

Use Claude Code to build pipelines against JSSI standards (CLAUDE.md / rules)

Required

Hands-on experience building and maintaining data pipelines in Microsoft Fabric, including Lakehouse architecture and OneLake

Proficiency with 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 practices, including Entra ID alignment

Experience exposing data products via APIs or MCP-style interfaces for downstream AI or analytics consumption

Active use of AI coding tools (such as Claude Code) as part of your development workflow — not aspirational, but current practice

Strongly preferred

Experience building data infrastructure specifically to support AI agents, ML models, or agentic pipelines

Familiarity with Power BI and Direct Lake connectivity

Experience working within engineering standards, documentation-first workflows, and structured code review practices

Exposure to MCP (Model Context Protocol) servers or similar AI data access patterns

Not required

People management experience — this is an individual contributor role

Aviation or MRO domain knowledge — curiosity and the ability to learn the business context matters more than knowing it on day one

WHO THRIVES IN THIS ROLE

This role is a great fit for someone who takes genuine ownership of data infrastructure — not just someone who builds pipelines when tickets arrive, but someone who thinks about the platform as a product with real consumers. You are already using AI tools to write and ship code faster. You care about data quality as a first principle, not a nice-to-have. And you want to be part of building something that directly enables the AI-first future of a company, not supporting a legacy stack.