Senior Azure AI Document Intelligence Engineer

ASA Techsol LLC; Irving (TX); On-site; USD 120,000 - 190,000; Full time

Job summary

ASA Techsol LLC in Irving, TX is seeking a Senior Azure AI Document Intelligence Engineer to design, train, evaluate, and continuously improve document-processing models for contracts and invoices. You will own extraction quality and be accountable for achieving 98–99% accuracy.

You will analyze invoices and contracts across suppliers, languages, and formats, define taxonomy, and evaluate Azure AI Document Intelligence capabilities including prebuilt, layout, custom neural, and template models.

Qualifications

• Bachelor’s or Master’s degree in Computer Science, Data Science, Artificial Intelligence, Engineering, or a related discipline.
• 4+ years of experience in machine learning, OCR, computer vision, NLP, or intelligent document processing.

Responsibilities

• Analyze invoice and contract variations across suppliers, countries, languages, formats, and scan-quality levels.
• Define the document taxonomy and extraction schema.
• Evaluate Azure AI Document Intelligence prebuilt and custom models for invoices and layouts.
• Build and train custom document classifiers and extraction models.
• Prepare, label, clean, balance, and version training data sets.
• Develop confidence-scoring and validation strategies for extracted fields.
• Establish thresholds and human-review rules for uncertain extractions.
• Create automated evaluation pipelines reporting accuracy, precision, recall, F1 score, and false-positive/negative rates.
• Monitor model drift and retrain as formats or requirements change.

Skills

Azure AI Document Intelligence

OCR

Machine Learning

NLP

REST APIs

Education

Bachelor’s or Master’s in CS/Data Science/AI/Engineering

Tools

Azure SDKs

JSON

Job description

er
Irving,

TX
We are seeking a Senior Azure AI Document Intelligence Engineer to design, train, evaluate, and continuously improve the document-processing models used for supply-chain contracts and invoi

ces.This engineer will own extraction quality and be directly accountable for achieving the project’s 98–99% accuracy objecti

ves.Key Responsibili

Key Responsibili

• tiesAnalyze invoice and contract variations across suppliers, countries, languages, formats, and scan-quality lev
• els.Define the document taxonomy and extraction schema
• dersContract meta
• dataPurchase-order refere
• ncesSupplier and customer informa
• tionDates, currencies, taxes, discounts, and to
• talsPayment terms, renewal dates, obligations, and termination cla
• usesTables and invoice line i
• temsEvaluate Azure AI Document Intelligence prebuilt invoice, layout, custom neural, custom template, classification, and composed-model capabilit
• ies.Build and train custom document classifiers and extraction mod
• els.Prepare, label, clean, balance, and version training and evaluation datas
• ets.Implement document preprocessing for rotation, skew, noise, resolution, page separation, and scan-quality iss
• ues.Develop confidence-scoring and validation strategies using field-level and OCR-level confidence sign
• ing:Subtotal, tax, and total reconcilia
• tionCurrency and date valida
• tionPurchase-order and supplier matc
• tionRequired-field and cross-field consistency ch
• ecksEstablish confidence thresholds and human-review rules for uncertain extracti
• ons.Perform error analysis by document type, supplier, field, language, and scan qual
• ity.Create automated evaluation pipelines reporting exact-match accuracy, precision, recall, F1 score, false-positive rates, and false-negative ra
• tes.Monitor model drift and retrain models when document formats or business requirements cha
• nge.Document model versions, training data, experiments, limitations, and release decisi
• ons.Collaborate with supply-chain, procurement, accounts-payable, legal, and engineering te
• ams.Required Qualificat

Required Qualificat

• ionsBachelor’s or master’s degree in Computer Science, Data Science, Artificial Intelligence, Engineering, or a related discipl
• ine.4+ years of experience in machine learning, OCR, computer vision, NLP, or intelligent document process
• ing.Hands-on experience with Azure AI Document Intelligence or a comparable enterprise document-processing platf
• lls.Experience with REST APIs, JSON, Azure SDKs, and asynchronous process
• ing.Experience training and evaluating document classification and field-extraction mod
• els.Strong understanding of accuracy, precision, recall, F1 score, confidence calibration, and test-set des
• ign.Experience extracting complex tables and variable-length line it
• ems.Experience creating labeled datasets and maintaining data-quality standa
• rds.Familiarity with invoices, purchase orders, contracts, or supply-chain docume
• nts.Strong analytical, debugging, and technical-documentation ski
• lls.

Preferred Qualificat

• ionsExperience with Azure Machine Learning, MLflow, Azure AI Search, or Azure Ope
• nAI.Experience with multilingual docume
• nts.Familiarity with contract clause extraction and legal-document process
• ing.Knowledge of ERP or procurement systems such as SAP, Oracle, Dynamics 365, Coupa, or Ar
• iba.Experience implementing active learning, model-drift monitoring, and human-in-the-loop workfl
• ows.Knowledge of data privacy and document-retention requireme
• nts.

Success Meas

• ures≥99% exact-match accuracy for approved critical fie
• lds.≥98% exact-match accuracy across all agreed fie
• lds.Accuracy maintained across suppliers, formats, and document-quality categor
• ies.Measurable reduction in manual corrections and review t
• ime.Documented improvement process for fields that miss their thresho
• lds.No production model deployed without passing the approved evaluation su
• ite.