Applied Materials
Product Intern, AI/ML Team
Led two ML initiatives: an internal document search chatbot achieving 96% accuracy, and a forecasting model predicting part shipment delays that saved millions in expedite costs.
My Role
On the AI/ML team at Applied Materials, I led two distinct machine learning projects from ideation to deployment, working at the intersection of data science and product development.
Project 1: Internal Document Search Chatbot
Built an AI-powered chatbot to help employees quickly search and retrieve information from Applied Materials' internal documentation. The chatbot used natural language processing to understand queries and return relevant documents, significantly reducing time spent searching for information.
Key Achievements
Achieved 96% accuracy in document retrieval. Led the project through all stages of the Data Science Process—from initial model creation, training, and fine-tuning to final deployment on the internal website.
Project 2: ML Forecasting Model for Shipment Delays
Developed a machine learning forecasting model to predict delays in the shipment of parts across Applied Materials' manufacturing operations. By analyzing historical data patterns, the model could identify potential delays before they occurred, allowing teams to proactively address issues.
Key Achievements
Improved prediction accuracy by 30%, helping reduce millions of dollars in expedite costs. Also developed scripts to evaluate LLM capabilities in parsing large-scale data files, testing performance across 10,000+ files simultaneously.