• Design, build, and deploy end-to-end AI pipelines for content moderation • Engage with operational business stakeholders to identify key initiatives • Extract text/tables from PDF documents using OCR (Tesseract, AWS Textract, Azure Form Recognizer) • Create/build labeling pipelines for training datasets • Train custom ML models (NLP/OCR) for document classification • Implement end-to-end pipeline: PDF → labeling → training → inference → API serving • Version control all code, datasets, and models using Git • Deploy models as REST APIs (FastAPI) • Work collaboratively to align business requirements with data and analytical solutions