Roles and Responsibilities:
Strong experience in machine learning/deep learning and computer vision background to help build industry-leading technology with a focus in document text extraction and parsing using OCR/ICR (Printed, scan, and Handwritten) across different languages.
Technologies:
Python: Pandas, NumPy, SciPy, PySpark, PyTorch, Matplotlib
Tools: Jupyter Notebook, Tableau, Power BI, Grafana
Techniques: Natural Language Processing (NLP) models, CNN DNN, Decision tree, Deep learning algorithms.
Note: Previous Experience in OCR Conversion of Medical Documents, Bank Statements, Office Documents such as (PDFs, Images etc)