Iury Souza
Android GDE, App Platform @ Klarna
Berlin, Germany
Actions
Google Developer Expert, Platform Eng @ Sumup
I'm a Google Developer Expert with over 10 years of hands-on experience with most of the mobile tech stack.
Curiosity driven, tinkering with computers and building things.
Area of Expertise
Topics
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.
Harness Engineering or How to Keep Agents on Track
AI coding agents move the bottleneck in software teams. Once a model can produce a decent patch in minutes, the scarce work is steering: giving it the right context, catching drift early, preserving architecture, and making failure easy to catch and cheap to fix.
This talk makes Harness Engineering concrete: the platform work around agentic coding. A useful harness turns the repository into an environment agents can operate inside safely. That means project commands, task-specific skills, architecture maps, coding rules, tests the agent can run and understand, feedback loops, and guardrails that keep changes observable and contained.
You will leave with a practical checklist for building your own harness: making your codebase more agent-ready, reducing drift and cognitive debt, while keeping accountability where it belongs: with humans.
Putting the Genie in the Bottle - A Crash Course on running LLMs on Android
Think running LLMs requires massive data centers? Think again. A new generation of efficient models is making on-device AI a reality, even on Android.
This session cuts through the hype to explore the practicalities of "Edge Inference." Learn why you'd ditch the cloud API calls for on-device processing.
We'll compare Google's AI Edge SDK and the MediaPipe LLM Inference API, highlighting the trade-offs Android developers face today. Understand the current limitations, the surprising capabilities of modern small models, and why experimenting with on-device LLMs now could give your app a competitive edge tomorrow.
Crash Course in building your First Gradle Plugin
A Gradle plugin is something that we use every day, but have you ever considered how they're created? What's behind the magic of the Kotlin DSLs provided by the plugins we use daily?
In this talk, we'll try to uncover the magic behind the Gradle plugin APIs and how to use them to build your own plugin. We'll explore the process of developing, debugging, testing, and finally publishing your grade plugin just like any other piece of software.
By the end of this, you'll learn how you can turn that custom Gradle task you've been copying and pasting across projects into a fully-fledged Gradle plugin!
Crash Course in building your First Gradle Plugin
A Gradle plugin is something that we use every day, but have you ever considered how they're created? What's behind the magic of the Kotlin DSLs provided by the plugins we use daily?
In this talk, we'll try to uncover the magic behind the Gradle plugin APIs and how to use them to build your own plugin. We'll explore the process of developing, debugging, testing, and finally publishing your grade plugin just like any other piece of software.
By the end of this, you'll learn how you can turn that custom Gradle task you've been copying and pasting across projects into a fully-fledged Gradle plugin!
Android Benchmarking and other stories
Benchmarking is a topic that will help you to take your app to the next level. Apps face bottlenecks and performance issues as they grow, and often continuing good programming practices will not suffice to keep their behavior on track. Integration of third-party APIs, complex access to hardware or just pushing the limits of what Android offers can often lead to a slower and buggier app.
With a proper benchmark strategy, you will be able to identify and resolve issues on your app before they become too big. This talk showcases the newly released framework from Google, JankStats, and how to use it on a real-world app. We will compare it with other already existing Google solutions. As a bonus, we will cover strategies and scenarios where we can integrate our benchmark suits on a CI/CD platform and keep track of regressions and improvements on our app.
next.app devcon Sessionize Event Upcoming
droidcon Lisbon 2025 Sessionize Event
2023 | Berlin | droidcon Sessionize Event
2023 | San Francisco | droidcon Sessionize Event
2022 | NYC | droidcon Sessionize Event
2022 | Berlin | droidcon Sessionize Event
2022 | San Francisco | droidcon Sessionize Event
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top