Custom OCR Model Developer

6 days ago


India beBeeOcr Full time ₹ 1,50,00,000 - ₹ 2,50,00,000
Job Overview

The AI/ML Engineer is responsible for developing and implementing custom OCR models using Azure Document Intelligence and AWS Textract.

Key responsibilities include automating document classification and data extraction from structured/unstructured inputs, such as PDFs and scanned images.

The successful candidate will build multilingual OCR workflows by integrating Azure Translator and apply NLP insights using AWS Comprehend.

They will also develop GenAI-powered solutions with AWS Bedrock and Azure OpenAI for semantic understanding, summarization, and contextual search of documents.

In addition, they will utilize AWS Rekognition for image-based document analysis and identity verification.

The ideal candidate will implement and optimize scalable pipelines for OCR output post-processing using Python, Java, or .NET.

Strong collaboration and communication skills are essential for working with cross-functional teams to gather requirements and deliver tailored, production-grade solutions.

The role requires a deep understanding of data privacy, security, and governance standards across cloud platforms.

Required Skills and Qualifications
  • 8+ years of experience in OCR technologies, intelligent document processing, and enterprise-scale AI/ML solutions
  • Expertise in Azure AI Services (Form Recognizer/Document Intelligence, Translator, OpenAI) and AWS AI/ML stack (Textract, Comprehend, Rekognition, Bedrock)
  • Strong coding skills in Python, Java, or .NET with hands-on experience in post-processing OCR outputs
  • Familiarity with AWS services (EC2, ECS, S3, Lambda, Step Functions) and Azure cloud environments
  • Deep knowledge of document layout analysis (tables, forms, key-value pairs)
  • Experience with NLP tools, translation APIs, and GenAI model training, fine-tuning, and deployment
  • Exposure to Consumer, Retail, and Logistics domain workflows (preferred)
  • Understanding of Terraform, CI/CD pipelines, DevOps practices, and Git (advantage)
  • Bachelors degree in Computer Science, IT, or equivalent (preferred)

  • OCR and Gen AI

    7 days ago


    India Recro Full time

    Responsibilities:- Design, train, and deploy custom OCR models using Azure Document Intelligence and AWS Textract- Automate document classification, data extraction from structured and unstructured formats (PDFs, scanned images, invoices, etc.)- Integrate OCR workflows with Azure Translator for multilingual document processing and AWS Comprehend for...

  • OCR and Gen AI

    7 days ago


    India Recro Full time

    Responsibilities: Design, train, and deploy custom OCR models using Azure Document Intelligence and AWS Textract Automate document classification, data extraction from structured and unstructured formats (PDFs, scanned images, invoices, etc.) Integrate OCR workflows with Azure Translator for multilingual document processing and AWS Comprehend for NLP-based...


  • India beBeeAiEngineer Full time ₹ 15,00,000 - ₹ 25,00,000

    As a skilled engineer, you will be instrumental in designing and deploying cutting-edge OCR models using leading technologies. This role requires expertise in machine learning algorithms and software development.Key ResponsibilitiesCreate custom OCR models leveraging Azure Document Intelligence and AWS Textract.Automate document classification and data...

  • Data Scientist

    7 days ago


    India beBeeDocument Full time ₹ 2,00,00,000 - ₹ 2,50,00,000

    Job Summary:Develop Intelligent Document Processing SolutionsDesign and deploy custom OCR models using Azure Document Intelligence and AWS Textract for image and document analysis.Implement scalable pipelines for OCR output post-processing using Python, Java, or .NET.Automate Data Extraction and ClassificationIntegrate Azure Translator and apply NLP insights...

  • AI/ML Engineer

    2 weeks ago


    India Recro Full time

    Job DescriptionResponsibilities- Design, train, and deploy custom OCR models leveraging Azure Document Intelligence and AWS Textract.- Automate document classification and data extraction from structured/unstructured inputs (PDFs, scanned images, invoices, etc.).- Build multilingual OCR workflows by integrating Azure Translator and apply NLP insights using...

  • AI/ML Engineer

    7 days ago


    India Recro Full time

    Responsibilities- Design, train, and deploy custom OCR models leveraging Azure Document Intelligence and AWS Textract.- Automate document classification and data extraction from structured/unstructured inputs (PDFs, scanned images, invoices, etc.).- Build multilingual OCR workflows by integrating Azure Translator and apply NLP insights using AWS Comprehend.-...

  • AI/ML Engineer

    7 days ago


    India Recro Full time

    Responsibilities Design, train, and deploy custom OCR models leveraging Azure Document Intelligence and AWS Textract . Automate document classification and data extraction from structured/unstructured inputs (PDFs, scanned images, invoices, etc.). Build multilingual OCR workflows by integrating Azure Translator and apply NLP insights using AWS...


  • India 9NEXUS Full time

    We are looking for an experienced Python Developer with expertise in web scraping and OCR to design and optimize data extraction solutions. The role involves building scalable scripts, integrating OCR workflows, and ensuring clean, structured data for downstream use.Key Responsibilities:- Develop and maintain Python scripts for web scraping from structured...

  • SAP SD

    2 weeks ago


    India Newforceltd Full time

    **SAP SD - SDM Sales order & e-com**: - 10-20 Years- Full Time Jobs- Market Rate- India**#Edi** **#Sfa** **#Ocr** **#Vmi** **#Erp** **- Experience in sales order entry channels (EDI, SFA, OCR) & sales orders impacted by the business operational model (VMI, consignment) - Experience in ERP organizational structure and data (sales organization,...


  • India beBeeData Full time ₹ 15,00,000 - ₹ 28,00,000

    We are seeking a seasoned Python Data Engineer to craft and refine data extraction solutions. The role involves designing scalable scripts, integrating optical character recognition (OCR) workflows, and ensuring high-quality, structured data for downstream use.Key Responsibilities:Develop and maintain Python scripts for web scraping from structured and...