azeebneuron
Work
  • Mar2025 - Present
    Docxster
    Machine Learning Intern
    • Building a proprietary, end-to-end document intelligence pipeline to replace Amazon Textract, targeting 40-60% cost reduction while creating a core automation asset for the company.
    • Developing a synthetic data generation pipeline using GANs to create 100,000+ custom document images, addressing the shortage of complex, real-world training data.
    • Creating DocStruct-YOLO, a YOLOv10-based model for Document Layout Analysis that accurately identifies tables, text, and figures as the foundation for our extraction system.
  • Jul2024 - Aug2024
    Sudha Gopal Krishnan Brain Centre
    Intern (Python, Deep Learning, Image Proccessing)
    • Implemented a RESTful API with Flask that leveraged deep learning models to perform feature extraction on raw brain images, thereby significantly accelerating the research and analysis pipeline.
    • Developed a Python pipeline to convert SVG brain annotations into validated GeoJSON format, utilizing geospatial libraries to enable accurate mapping and interoperability with advanced analysis tools.
    • Deployed a fine-tuned ResNet-50 model to perform similarity analysis on brain region images, generating quantitative scores to uncover novel insights into anatomical patterns and relationships.