Azure AI Document Intelligence Engineer

Job Title: Senior Azure AI Document Intelligence Engineer (OCR)

Location: Irving, TX – Hybrid (3 days onsite)
Duration: Contract
Experience: 10+ Years
Education: BE/ME/BTech/MTech/BSc/MSc or equivalent

Job Overview

We are seeking a Senior Azure AI Document Intelligence Engineer with strong hands-on experience in OCR, Machine Learning, Computer Vision, NLP, and Intelligent Document Processing.

The ideal candidate will design, train, optimize, and deploy AI-powered contract and invoice document-processing solutions using Azure AI Document Intelligence, Azure Databricks, Azure Machine Learning, MLflow, Azure AI Search, Azure OpenAI/GenAI, Python, and SQL.

The role will focus on achieving 98–99%+ extraction accuracy across complex supply-chain, procurement, invoice, and contract documents.

Key Responsibilities

• Analyze invoice and contract variations across suppliers, countries, languages, formats, and scan-quality levels.

• Define document taxonomy and extraction schemas for invoices, contracts, purchase orders, supplier/customer information, dates, currencies, taxes, totals, payment terms, clauses, and line items.

• Work with Azure AI Document Intelligence prebuilt, layout, custom neural, custom template, classification, and composed models.

• Build, train, evaluate, and optimize custom document classification and extraction models.

• Prepare, label, clean, balance, version, and maintain high-quality training/evaluation datasets.

• Implement document preprocessing for rotation, skew, noise, resolution, page separation, and poor scan quality.

• Develop confidence-scoring and validation frameworks using OCR and field-level confidence signals.

• Implement validation rules for subtotal/tax/total reconciliation, currency/date validation, PO and supplier matching, duplicate detection, and cross-field consistency.

• Establish confidence thresholds and human-in-the-loop review processes for uncertain extractions.

• Perform detailed error analysis by document type, supplier, field, language, and document quality.

• Build automated evaluation pipelines measuring accuracy, precision, recall, F1 score, false positives, and false negatives.

• Monitor model performance and drift and retrain models as document formats and business requirements evolve.

• Maintain documentation for model versions, training datasets, experiments, limitations, and production release decisions.

• Collaborate with Supply Chain, Procurement, Accounts Payable, Legal, and Engineering teams.

Mandatory Skills

• 4+ years of hands-on experience in Machine Learning, OCR, Computer Vision, NLP, or Intelligent Document Processing.

• Strong experience with Azure AI Document Intelligence or a comparable enterprise document-processing platform.

• Strong Python development skills.

• Experience with REST APIs, JSON, Azure SDKs, and asynchronous processing.

• Experience training and evaluating document classification and field-extraction models.

• Strong understanding of accuracy, precision, recall, F1 score, confidence calibration, and test-set design.

• Experience extracting complex tables and variable-length invoice line items.

• Experience creating and maintaining labeled datasets and data-quality standards.

• Experience working with invoices, purchase orders, contracts, or supply-chain documents.

• Strong analytical, debugging, problem-solving, and technical documentation skills.

Preferred Skills

• Azure Machine Learning

• MLflow

• Azure Databricks

• Azure AI Search

• Azure OpenAI / GenAI

• Multilingual document processing

• Contract clause extraction and legal-document processing

• ERP/procurement platforms such as SAP, Oracle, Dynamics 365, Coupa, or Ariba

• Active learning and model-drift monitoring

• Human-in-the-loop workflows

• Data privacy and document-retention requirements

• SQL

Success Measures

• Achieve ≥99% exact-match accuracy for approved critical fields.

• Achieve ≥98% exact-match accuracy across agreed extraction fields.

• Maintain accuracy across different suppliers, formats, languages, and document-quality levels.

• Reduce manual corrections and document-review time.

• Establish a measurable continuous-improvement process for fields below accuracy thresholds.

• Ensure no production model is deployed without successfully passing the approved evaluation suite.

Core Technology Stack

Azure | Azure AI Document Intelligence | Azure Databricks | Azure Machine Learning | MLflow | Azure AI Search | Azure OpenAI | GenAI | Python | SQL | OCR | Machine Learning | Computer Vision | NLP | Intelligent Document Processing

If this opportunity aligns with your experience, please share your updated resume, current location, work authorization, availability, and expected rate.