Real-Time AI: Deploying Machine Learning Models in Web Apps

In this hands-on module, participants will learn how to deploy a machine learning model as a real-time API and integrate it into a simple web application. Using FastAPI for backend deployment and Streamlit for the UI, students will build a functional AI-powered web app that takes user input, processes it with an ML model, and returns predictions. This module is designed for students with basic coding experience who want to bridge the gap between machine learning and real-world applications. By the end, participants will have a working AI system running on their local machine. The course will be held in English.

Davide Gamba
I hold a Bachelor’s degree in Data Science & AI and work as an MLOps and Data Engineer at Artificialy in Lugano, where I specialize in machine learning pipelines, model deployment, and AI infrastructure. My experience allows me to break down complex AI concepts into practical applications. I want to teach this module because ML deployment is often overlooked, yet it’s a crucial skill for turning AI models into usable products. I aim to provide a structured, hands-on experience so students can apply these skills immediately. Additionally, I enjoy sharing knowledge and helping others bridge the gap between theoretical AI and real-world implementations.