- Engineered a Watson Assistant AI chatbot utilizing NeuralSeek, Watson Discovery, & Watson Assistant on the IBM Cloud platform.
- Implemented Python scripts leveraging libraries such as BeautifulSoup, Scrapy, Requests, and Selenium for web scraping and data collection from 5,000+ health-related URLs and documents, building comprehensive datasets for chatbot training.
- Conducted data cleaning and preprocessing using pandas and NumPy to ensure high-quality data for AI model training.
- Developed custom code to extract and process Spanish audio from videos using FFmpeg and pydub, integrating this with DeScript, ElevenLabs, and HeyGen to create AI-generated Spanish versions of English YouTube videos.