Intelligent Document Processing / OCR Engineer - Part Time

HeiTech Services, LLC; Hyattsville (MD); On-site; USD 110,000 - 140,000; Full time

Job summary

HeiTech Services seeks an Intelligent Document Processing / OCR Engineer to design and implement document-processing capabilities that convert electronic records into structured, traceable information. The role covers OCR, image preprocessing, layout analysis, and developing classification and extraction methods.

The engineer will configure OCR models, establish validation rules, confidence scores, and human-review thresholds, working with cross-functional teams to support government-oriented

Qualifications

• Bachelor’s degree in CS or a related technical field.
• Five years of relevant experience in document processing or data engineering.
• At least two years hands-on OCR, document classification, and structured extraction.
• Experience with scanned or mixed-format documents and validation rules.
• Experience implementing confidence scoring and human-in-the-loop reviews.
• US Citizenship and ability to obtain Public Trust.

Responsibilities

• Assess document collections and determine OCR and processing approaches.
• Configure OCR, image preprocessing, and layout-analysis for various documents.
• Develop document-classification methods and extraction schemas.
• Establish confidence scores, validation rules, and exception handling.
• Support automated processing workflows and documentation for deployment.

Skills

OCR

Document processing

Data engineering

Automation

Machine learning

Quality assurance

Testing

Education

Bachelor’s degree in CS/Engineering

Tools

Azure AI Document

APIs

Logic Apps

Power Automate

Azure Functions

Job description

Description

Designs and implements the intelligent document-processing capabilities required to convert electronic records into reliable, structured, and traceable information. The Intelligent Document Processing / OCR Engineer assesses the document corpus and document quality; applies OCR, image preprocessing, and layout analysis where required; supports duplicate detection; develops document-classification and structured field-extraction methods; and establishes confidence scores, validation rules, exception-handling procedures, and human-review thresholds.

Designs and implements the intelligent document-processing capabilities required to convert electronic records into reliable, structured, and traceable information. The Intelligent Document Processing / OCR Engineer assesses the document corpus and document quality; applies OCR, image preprocessing, and layout analysis where required; supports duplicate detection; develops document-classification and structured field-extraction methods; and establishes confidence scores, validation rules, exception-handling procedures, and human-review thresholds. The Engineer configures and tunes OCR models, preprocessing techniques, classification methods, extraction schemas, confidence thresholds, and validation logic based on testing results and representative document samples. The position establishes measurable evaluation methods for OCR quality, classification accuracy, field-extraction accuracy, exception rates, and human-review requirements. Processing configurations, quality results, known limitations, and operating procedures are documented to support explainability, repeatability, troubleshooting, and knowledge transfer. The Engineer works within the overall architecture established by the Microsoft Cloud Solution Architect / Technical Lead and coordinates closely with platform, data, security, quality assurance, AI search, and Government subject-matter personnel. The position also supports automated processing of newly added or modified documents so that files can be assessed, preprocessed, classified, extracted, validated, and routed for human review or downstream indexing with minimal manual intervention. The greatest level of effort is expected during corpus assessment, OCR and preprocessing configuration, classification and extraction development, validation-rule definition, quality testing, and document-processing automation.

Key Responsibilities

• Assess document collections, formats, and quality to determine appropriate OCR and processing approaches.
• Configure and tune OCR, image preprocessing, and layout-analysis capabilities for scanned, image-based, degraded, and digitally generated documents.
• Develop document-classification methods, taxonomies, and associated processing rules.
• Develop structured field-extraction schemas, metadata mappings, validation rules, and extraction logic.
• Establish confidence scores, acceptance thresholds, exception criteria, and human-review requirements.
• Design and support exception-handling and human-validation workflows for incomplete, ambiguous, or low-confidence processing results.
• Support duplicate-detection and document-quality controls within the processing workflow.
• Develop or support automated processing workflows for newly added or modified documents, including ingestion, classification, extraction, validation, and exception routing.
• Define, measure, and tune OCR quality, classification accuracy, and field-extraction accuracy using representative document samples.
• Document processing configurations, quality results, known limitations, validation procedures, and operating instructions to support testing, deployment, and knowledge transfer.

Requirements

• Bachelor’s degree in computer science, data science, information systems, engineering, or a related technical discipline.
• Five years of relevant experience in document processing, data engineering, automation, machine learning, or a related technical field.
• At least two years of hands-on experience with OCR, intelligent document processing, document classification, structured data extraction, or comparable technologies.
• Experience processing scanned, image-based, degraded, digitally generated, or mixed-format document collections.
• Experience developing document-classification, field-extraction, validation, or metadata-processing capabilities.
• Experience implementing confidence scoring, exception handling, validation rules, or human-in-the-loop review processes.
• Experience testing and evaluating OCR, classification, or extraction performance using defined quality measures.Must be a US Citizen and ability to obtain and maintain a Public Trust.

Preferred

• Experience with Azure AI Document Intelligence or comparable intelligent document-processing platforms.
• Experience automating document-processing workflows using APIs, scripts, Azure Functions, Logic Apps, Power Automate, or comparable technologies.
• Experience integrating document-processing capabilities with document repositories, databases, content-management systems, or cloud platforms.
• Experience supporting Federal Government, Government cloud, or other regulated environments.

This position is contingent upon contract award. HeiTech Services is proactively identifying qualified candidates in anticipation of a potential federal contract award. Qualified applicants may be contacted for prescreening and interviews prior to award. Employment is contingent upon successful contract award and completion of all required pre-employment and security requirements.

HeiTech Services is an Equal Opportunity Employer. We consider all qualified applicants without regard to race, color, religion, sex (including pregnancy, sexual orientation, and gender identity), national origin, age, disability, veteran status, or any other protected status under applicable law.

If you require a reasonable accommodation during the application process, please contact us at [e-mail].

HeiTech Services may utilize technology-assisted tools, including artificial intelligence, to support the review of application materials. These tools are used to enhance efficiency; however, all hiring decisions are made by human reviewers in accordance with federal hiring guidelines.