As an AI & Data Intern at Navigating AWEtism, my role involved developing AI chatbots, building comprehensive datasets through web scraping, and creating multilingual content through advanced audio processing and AI-powered language generation.
Key Projects & Technologies
AI development, data engineering, and multimedia processing
Watson Assistant AI Chatbot
Implementation
Engineered and deployed a sophisticated AI chatbot system to answer key questions from users and provide research-based information for autism support and accessibility.
Technology Stack
IBM Cloud Platform, Watson Assistant, Watson Discovery, NeuralSeek
Data Engineering & AI Training
Data Collection
Collected data from 5,000+ health-related URLs and documents to build comprehensive datasets for AI model training and chatbot development.
Data Processing
Implemented comprehensive data cleaning and preprocessing workflows using pandas and NumPy to ensure high-quality data for AI model training.
Technologies
Python, BeautifulSoup, Scrapy, Requests, Selenium for web scraping; pandas and NumPy for data processing and AI training optimization.
Multilingual AI Video Processing
Innovation
Created AI-generated Spanish versions of English YouTube videos through advanced audio processing and AI-powered language generation.
Technology Integration
Leveraged FFmpeg, pydub, DeScript, ElevenLabs, and HeyGen to extract, process, and transform audio content across languages.
Key Takeaways
Professional growth and learning outcomes
AI for Social Good
Learned to develop AI solutions that address real-world accessibility challenges, understanding the importance of ethical AI development and user-centered design.
Data-Driven Development
Developed skills in creating and curating training datasets, implementing ML pipelines, and measuring impact through quantitative metrics.