Job Opportunity: OCR Engineer at Birlasoft

Are you an experienced OCR Engineer with a robust background in data science? We're looking for someone with hands-on experience in Microsoft Document Intelligence and GPT-4 Vision Models to join our dynamic team at Birlasoft. In this role, you'll play a critical part in developing and implementing OCR solutions that address diverse document and image scenarios, driving innovation and optimization in our OCR systems.

Key Responsibilities

• Implement OCR on various unstructured documents (e.g., images, PDFs) to curate high-quality data for LLM training.
• Design, develop, and deploy OCR solutions tailored to different document and image types, leveraging advanced OCR tools such as Microsoft Document Intelligence and GPT-4 Vision.
• Conduct thorough analyses of OCR requirements and document/image characteristics to identify optimal OCR strategies and algorithms.
• Collaborate with software engineers, data scientists, and product managers to integrate OCR capabilities into existing systems and workflows.
• Enhance OCR accuracy and robustness through expertise in data preprocessing, feature extraction, and machine learning, especially for challenging scenarios like low-quality images or complex layouts.
• Continuously evaluate and benchmark OCR performance against industry standards using metrics and testing methodologies for iterative improvements.
• Stay updated with the latest advancements in OCR technologies, data science methodologies, and related fields. Contribute to the company's knowledge base through research and experimentation.
• Provide technical guidance and mentorship to junior team members, fostering a culture of learning and innovation within the OCR engineering team.

Qualifications

To be considered for this role, you must have:

• Proficiency in AI Search and Vector Database creation for relational databases and unstructured data.
• Expertise in Azure app services for building and deploying AI applications using cloud services.
• Deep expertise in Azure SQL, Azure Data Factory, Linked Services, and Azure Synapse.
• 8+ years of hands-on experience in OCR engineering with a proven track record of developing and deploying OCR solutions in real-world applications.
• Strong programming skills in languages such as Python, C++, or Java, and experience with relevant libraries and frameworks (e.g., OpenCV, TensorFlow, PyTorch).
• Comprehensive knowledge of Microsoft Document Intelligence and other Microsoft Azure Computer Vision services.
• Extensive familiarity with OCR tools and frameworks, including Microsoft Document Intelligence, GPT-4 Vision, and Tesseract.
• Solid understanding of data science principles and methodologies, with experience in machine learning, deep learning, and natural language processing (NLP) techniques.
• Expertise in structuring OCR output in relational databases for large language model training.
• Excellent communication and teamwork skills, and the ability to work effectively in a collaborative, cross-functional environment.
• Strong analytical and problem-solving abilities, with keen attention to detail and a passion for continuous improvement.

If you meet the above qualifications and are eager to drive innovation in OCR technology, we would love to hear from you!

Company Name: Birlasoft

Job Title: OCR Engineer