Gabriel Volpi
Android Software Engineer at iFood
I am an Android Software Engineer with over 5 years of experience building large-scale mobile applications, currently working at iFood, one of the largest food delivery platforms in the world. As part of the Order Delivery team, I work on critical flows that impact millions of users, with a strong focus on performance, scalability, monitoring, reliability, and product-driven engineering.
My recent work has focused on Edge AI and on-device machine learning, exploring how Android’s ML Kit Prompt APIs, AICore, and generative models can be used to turn AI capabilities into real product experiences. I am especially interested in the trade-offs between cloud and on-device AI, including latency, privacy, cost, scalability, and user value.
I hold a degree in Control and Automation Engineering from UNICAMP and I am currently pursuing a postgraduate degree in Software Engineering. I am also actively involved in the Android community, sharing practical experiences about mobile architecture, production monitoring, and on-device AI. Most recently, I presented at AndroidMakers by Droidcon Paris, discussing practical approaches to bringing Edge AI into production-grade Android applications.
Practical On-Device Al: Turning Edge Al into Real Features
Building a solid mental model of Edge AI and hybrid patterns is the first step toward transforming UI state and structured data into reliable AI inputs. This session moves past the hype to show how on-device AI can power actual user-facing features while maintaining low latency, privacy, and predictable behavior by keeping sensitive data off the cloud.
We will break down the engineering trade-offs, context design, and safety mechanisms required to close the agentic loop. You’ll leave with practical proof-of-concepts for building AI features that are useful, stable, and ready for production.