Data Engineer / Document AI Engineer

Introduction

We are looking for a highly skilled Data Engineer / Document AI Engineer to join our team. As a Data Engineer / Document AI Engineer, you will be responsible for building and maintaining production data pipelines, with a focus on document processing, OCR, and information extraction at scale. You will work with various technologies, including Python, OCR & Document Processing, Azure AI Document Intelligence, SQL, and more, to ensure the accuracy and efficiency of our data processing systems.

Responsibilities

• Build and maintain production data pipelines for document processing, OCR, and information extraction.
• Work on image preprocessing tasks such as deskew, denoise, binarization, and contrast handling to improve scan quality.
• Utilize large language models for structured extraction from unstructured text and design prompts for reliable field-level output.
• Implement entity resolution and record linkage techniques to ensure data accuracy and completeness.
• Create and maintain relational data models using SQL.
• Measure data quality quantitatively and implement strategies to improve data accuracy.
• Ensure compliance with federal cloud security standards such as FedRAMP and CUI.

Requirements

• Five or more years of experience building production data pipelines, with at least two years in document processing, OCR, or information extraction.
• Strong Python skills and the ability to manage data pipelines from ingestion through storage.
• Hands-on experience with cloud document intelligence services, preferably Azure AI Document Intelligence.
• Experience in image preprocessing for degraded scans and structured extraction from unstructured text.
• Knowledge of entity resolution and record linkage techniques.
• Proficiency in SQL and relational data modeling.
• Ability to measure data quality quantitatively and ensure data accuracy.
• United States citizenship and eligibility for federal public trust suitability screening.

• Experience with Azure Government or Microsoft 365 GCC delivery and FedRAMP-authorized service constraints.
• Knowledge of Microsoft Graph API, SharePoint Online, Azure Functions, and other Azure services.
• Experience with Power Automate for event-driven triggers.
• Prior federal contract delivery experience is a plus.
• Knowledge graph construction or graph query experience.