Jordan Voves

Data Architect (2025–Present), Senior Data Engineer (2022–2025)

Joined as one of the first members of a new AI team, and served as the sole Data Engineer for nearly three years, leading the design and build of the data platform foundations in a blank Azure environment. Architected a cutting-edge Databricks Lakehouse platform and supporting services that enabled multiple AI products and real-time evaluation. Promoted to Data Architect to guide platform evolution and lead cross-functional delivery.

Key Products

• Insights and Actions – Prototyped an approach to generate automation insights from CSR correction data. Presented it with a Databricks App (Insights Lab) using Lakebase; overwhelmingly positive reception led the business to prioritize it, and I drove it through delivery to production as technical lead of a 7-person pod (AI Engineer, 3 SWE, FE, UI Designer, PM).
• Navigator – Designed and delivered a customer-facing app with KPIs and metrics giving customers direct visibility into automation performance and adoption.
• Express (AI Document Extraction) – Delivered the company’s flagship AI extraction product by architecting the data and evaluation layers that enabled rapid iteration and reliable accuracy.

Context & Evaluation Frameworks

• Built a unified evaluation framework using ground-truth metrics for extraction and LLM-as-judge for tasks without labels, enabling rapid iteration and confident production releases.
• Developed a context moat to enrich inference, including PNR (vector search for missing part numbers), Trading Partner Insights (corrections, interactions, and context), Layout/TP Detection (layout embeddings), and few-shot examples (user-approved extractions). These systems powered continuous improvement and productization of the AI Document Processing system.

Platform Architecture

• Championed Databricks as the company-wide AI/data platform.
• Built Spark streaming pipelines with Workflows and Asset bundles, deployed via Azure DevOps, with unit and integration testing.
• Established Unity Catalog governance, evolving the lakehouse into a secure, production-grade platform that supports AI products and real-time monitoring.

Visualization & Business Enablement

• Built dashboards across finance, product, CS, and engineering, including the AI Document Processing evaluation dashboard.
• Created Genie spaces for retrieval-augmented analytics, and maintained a semantic layer (via Pydantic) to improve the effectiveness of Genie and AI/BI.

Sr Data Engineer (Jan 2022 - Jul 2022), Data Engineer (2018-2022)

• Led migration from legacy MSSQL workflows to a modern data lake architecture.
• Designed and implemented an Airflow-based orchestration platform, retiring dozens of legacy ETL jobs and enabling scalable production pipelines.
• Rebuilt large-scale aggregations (3B+ records) using PySpark and Presto, cutting runtimes from 48 hours to 20 minutes and doubling reportable data for national television products.
• Mentored junior engineers and data scientists on Python design patterns and AWS technologies (Kinesis, Glue, Lambda, ECS, Athena)