Data Science Engineer

Responsibilities:

• Design and implement robust pipelines for extracting data from structured, semi-structured, and unstructured documents.
• Apply OCR techniques to digitise and interpret handwritten and scanned content using tools like Tesseract, EasyOCR, or AWS Textract.
• Develop NLP models for entity recognition, document classification, and semantic understanding.
• Build and maintain Python-based frameworks for document parsing, preprocessing, and feature engineering.
• Collaborate with cross-functional teams to integrate document intelligence into business workflows.
• Evaluate and optimise model performance for accuracy, latency, and scalability.
• Maintain documentation and ensure compliance with data governance and security standards.

Requirements:

• 4+ years of hands-on experience in Python programming and Machine Learning.
• Strong proficiency in OCR tools (e. g., Tesseract, Google Vision, Azure Form Recogniser).
• Solid understanding of NLP techniques (e. g., tokenisation, named entity recognition, topic modelling).
• Experience with document processing libraries e. g., PyMuPDF, pdfminer, OpenCV.
• Familiarity with deep learning frameworks (e. g., TensorFlow, PyTorch) is a plus.
• Ability to work independently and manage end-to-end solution delivery.