Sessions

A quick tour into Google's Secure AI Framework (SAIF)

Speakers: Patty O'Callaghan

Join me for an engaging talk where we explore Google's Secure AI Framework (SAIF), an essential guide to enhancing AI security. This session will break down SAIF, examining its core elements that address AI-specific threats, promote security by design, and encourage industry-wide collaboration. Discover how SAIF is setting new benchmarks for secure AI deployments, with actionable insights for implementation, real-life examples, and a glimpse into the future of AI security.

Talk

Accelerate building Al applications with Cloud Run.

Speakers: Michael Mekuleyi

In this session, we'll explore how to leverage Cloud Run to rapidly develop and deploy AI applications. Learn how to seamlessly integrate AI models, scale effortlessly with demand, and reduce operational overhead. Whether you're building real-time inference services or batch processing tasks, this talk will provide practical insights and hands-on demonstrations to accelerate your AI projects using Cloud Run. Join us to discover best practices and unlock the full potential of serverless computing in the AI space.

Talk

Adding Homescreen Widgets to your Flutter App

Speakers: Anton Borries

In this workshop you will add Homescreen Widgets to your Flutter Apps. Recent findings by Duolingo have shown that Homescreen Widgets are a great way of increasing user interactions with your app. And provide easier ways for your users to engage with your Apps. This workshop will cover: - What are Homescreen Widgets - How to add Homescreen Widgets to your App - Display your Flutter Widgets on a native Homescreen Widget - Call Dart Code from your Homescreen Widget for interactivity

Workshop

Android + Gemma: Building offline AI-powered apps

Speakers: Tom Colvin

Yes, you can run generative AI models locally on your Android phone! There are many benefits to this: - It improves privacy, since nothing leaves the device - It works fully offline - It saves money on cloud-based services. In this talk I will show how to build a fully-offline Android app with generative AI capabilities. We'll see: - What MediaPipe is and how we can integrate it into an app - How to obtain and use the latest Gemma models - What kinds of tasks can be accomplished on device vs in the cloud - Hardware requirements and performance expectations

Talk

Are Large Language Models Good? How we quantify the performance of LLMs.

Speakers: Lisa Carpenter

Many people are familiar with the outputs and apparent capabilities of large language models, with gut feelings about whether a model seems high performance or not. But few are aware of how we benchmark the performance capabilities of the different large language models. This talk explores the different measures and metrics we use to quantify the performance of large language models, as well as looking at the necessity of human in the loop and ethical concerns.

Talk

Avoid common LLM pitfalls

Speakers: Mete Atamel

It’s easy to generate content with a Large Language Model (LLM), but the output often suffers from hallucinations (fake content), outdated information (not based on the latest data), reliance on public data only (no private data), and a lack of citations back to original sources. Not ideal for real-world applications. In this talk, we’ll provide a quick overview of the latest advancements in multi-modal LLMs, highlighting their capabilities and limitations. We’ll then explore various techniques to overcome common LLM pitfalls, including Retrieval-Augmented Generation (RAG) to enhance prompts with relevant data, ReACT prompting to guide LLMs in verbalizing their reasoning, Function Calling to grant LLMs access to external APIs, and Grounding to link LLM outputs to verifiable information sources, and more.

Talk

Building a journalling app with Vertex AI in Firebase

Speakers: Marina Coelho

This talk will explore building an AI-powered Android app. I'll show you how I used Vertex AI in Firebase and other Firebase services to create a journalling app that helps women navigate the female experience with music, literature and films

Talk

Building Dynamic AI Chat with Firebase Vertex AI SDK in FlutterFlow: Empowering App Developers

Speakers: Maggie McRoskey

Join us for an exciting dive into building a powerful, dynamic AI chat application using Google's Vertex AI integrated with Firebase SDKs, all within FlutterFlow—a visual development platform that lets you build Flutter applications effortlessly. This session will guide you through leveraging Vertex AI in Firebase to create smart, secure, and responsive chat systems, while taking advantage of FlutterFlow's visual app-building tools for speed, customizability, and full ownership of your code. Whether you're a beginner or an experienced developer, this talk will offer practical insights into harnessing AI-driven features with minimal code and maximum efficiency in modern app development.

Talk

Building for the Future of Android

Speakers: Fung Lam

This session will cover recent changes and features in Android 15. What should developer do when building apps targeting the next version of Android. And what is coming in 2025.

Talk

Effortless optimization of Flutter apps: performance tips for developers

Speakers: Vadym Pinchuk

In this session, we’ll dive into effortless yet impactful ways to optimize your Flutter applications. Performance improvements don’t always require a full rewrite—sometimes, small adjustments can lead to big gains. We'll explore practical tips and tricks for enhancing app speed, responsiveness, and efficiency with minimal effort. From reducing widget rebuilds to handling large data efficiently and managing state effectively, this talk will provide developers with actionable insights to deliver a smoother user experience. Whether you’re a beginner or an experienced Flutter dev, you’ll walk away with easy-to-apply techniques to optimize your apps without breaking a sweat. Perfect for beginners and experienced developers looking to fine-tune their Flutter projects with maximum results and minimal complexity!

Talk

Empowering Your Flutter Apps with AI Using Firebase GenKit

Speakers: Renuka Kelkar, Sumith Damodaran

Updated Description: In this session, learn what Firebase GenKit is and how it empowers your Flutter applications with cutting-edge AI capabilities. We’ll walk through the steps to seamlessly integrate Firebase GenKit into your Flutter app, making it easier than ever to add intelligent features like natural language processing, predictive analytics, and personalized recommendations. Discover how Firebase GenKit stands out from other AI options in terms of simplicity, scalability, and deep integration with the Firebase ecosystem. Whether you're new to AI or an experienced developer, this talk will provide you with practical knowledge and insights to create smarter, more innovative mobile experiences.

Talk

Enhanced Platform Engineering: A Guide to Infrastructure Modernization

Speakers: Rohit Ghumare

In the rapidly evolving landscape of cloud computing, Google Cloud emerges as a pivotal tool for infrastructure modernization and platform engineering. This meetup delves into the strategic integration of Google Cloud services for developing robust internal platforms, focusing on leveraging existing cloud functionalities to streamline both development and operational processes. Key topics include understanding the user-centric approach in platform engineering, forming dedicated, cross-functional teams for platform development, and transitioning from traditional project metrics to product KPIs for measuring platform success. Additionally, the concept of 'Golden Paths' in engineering execution will be explored, emphasizing the importance of clear, self-service templates for common tasks, thereby enhancing developer productivity and project consistency. This session aims to equip participants with practical insights and strategies for avoiding common pitfalls in platform engineering projects, while fully leveraging the capabilities of Google Cloud.

Talk

Event Driven and Serverless: the perfect combo in GCP

Speakers: Mazlum Tosun

Event-Driven Architectures offer the advantage of significantly reducing latency when processing and integrating data into our systems. When combined with Serverless components, we can achieve reduced costs. In on-premises environments, however, the setup can be cumbersome due to the required infrastructure. Most cloud providers offer services that simplify the implementation of this architecture. But how do you navigate through the vast array of options? In this talk, we will demonstrate how Google Cloud streamlines the implementation of a fully Event-Driven and Serverless architecture. Using data from the latest Football World Cup, I will illustrate how to set up this type of architecture to calculate player stats by team. And yes, we'll see that Kylian Mbappé performed quite well!

Talk

Extending the Web - explore AI with WebExtensions

Speakers: Oliver Dunk

Did you know that with a basic knowledge of HTML, CSS and JS, you can build your own extension? This makes extensions (built using the cross-browser WebExtensions APIs) a great platform to get started with AI. In this talk, I’ll share what we’re already seeing developers build with AI in extensions and some of the newer possibilities. We’ll look at how to use various APIs and models from an extension and the different architectures that might make sense for your next project.

Talk

Firebase + SQL: an introduction to Data Connect

Speakers: Rosário Fernandes

Firebase is famously known for its NoSQL databases, but this year a new relational database service was added to the platform: Firebase Data Connect. In this talk, I’ll give an introduction to what Data Connect is about, how to get started with it in a Flutter application and how to integrate it with Firebase Authentication to secure your data. You’ll learn: - How to setup Data Connect with a Postgres SQL database - How to write GraphQL queries and mutations for your database - How to generate the Dart SDK to use it in a Flutter app - How to test it locally with the emulators and later deploy to the Cloud

Talk

Firebase Fundamentals: Structuring Your NoSQL Data for Scalability and Reporting

Speakers: Jason Berryman

Firebase offers a powerful and flexible NoSQL database solution, enabling real-time data synchronization and effortless scalability for your applications. However, designing your data structure for optimal performance and reporting can be challenging. In this session, we'll delve into the fundamentals of Firebase's NoSQL database and explore key principles for effectively structuring your data to achieve scalability while enabling SQL-based reporting capabilities. We'll cover topics like: Data Modeling Best Practices: Understand how to model your data in a way that promotes efficient queries and avoids common pitfalls. Denormalization for Performance: Learn how to strategically denormalize data to optimize read performance and minimize data retrieval costs. Indexing Strategies: Discover the importance of indexing and how to implement indexes effectively to speed up queries. SQL Integration for Reporting: Explore strategies for integrating SQL-based reporting tools with your Firebase data, including tips for data transformation and export. Real-World Examples: Analyze practical examples that illustrate how to apply these principles to real-world Firebase projects. By the end of this session, you'll have the essential knowledge and strategies to design Firebase data structures that can scale seamlessly with your growing user base and application complexity, while also empowering you to leverage the power of SQL for comprehensive reporting and analytics.

Talk

Gemma for Everyone: Your First Steps with Open Models and AI

Speakers: Gus Martins

Dive into the world of open models and AI with Gemma! This workshop will guide you through the basics of using Gemma, Google's powerful family of language models. Learn how to harness Gemma's capabilities for tasks like text generation, question answering, and more. We'll also explore how to fine-tune Gemma on your own data, allowing you to create custom AI solutions tailored to your needs. No prior experience with large language models is required!

Workshop

Getting started on Android UI design hub

Speakers: Hannah Olukoye

The Android Design Hub is a valuable resource that empowers Android developers to create uniform designs for all Android form factors. Incorporating material design for stunning and user-friendly interfaces for Android apps. While I am not a naturally gifted designer, tools like these have greatly improved my ability to create impactful user interfaces. Recognizing the importance of user interface design in gaining a competitive edge in the tech field, especially given my non-tech background. I am inspired to share my knowledge and experiences through the Android Design Hub. In this session, we will explore the changing landscape of Android UI design together, collaborate on innovative solutions, and inspire one another to push the limits of what is possible. For example, the Android Mobile Figma Kit

Talk

Glitz and glam✨r: the compose edition

Speakers: Eliza Camber

Android and its apps have come a long way in the past years when it comes to the UI. While a clean UI is the foundation of a good app, you can only provide your users the full experience by adding meaningful animations. Animations can make your app look more polished and fun; the biggest benefit though is that they can (and should) provide visual cues to the user about what the app is doing. In this talk, we will see how we can code some of the most common animation scenarios using the various Jetpack Compose Animation APIs.

Talk

How to use Gemini without getting caught

Speakers: Aldan Creo

Join us as we explore the world of detecting AI-generated text, such as what you get from Gemini. Have you ever wondered how experts uncover it? We'll spill the beans! We'll start from scratch, briefly explaining how the generation of text using AI works. No previous background in the field is required! Then, we'll discuss classifier systems for detection, black and white box models, watermarking, and manual techniques for detection—cool stuff to keep in your toolbox! But here's the twist—these systems are not foolproof. There are ways to get around them, and we'll explore how. Ready to uncover the mysteries? See you there!

Talk

Level up your public speaking: the not-so-obvious techniques

Speakers: Natalie Godec

Is public speaking only about what you know and how confident you are? Is having good slides and rehearsing them while drinking your morning coffee enough to deliver a good talk? Is there space for creativity in technical presentations? Join this workshop to find out!

Workshop

LLMs vs LVMs

Speakers: Moisés Martínez

Generative artificial intelligence has given rise to two key technologies that are transforming various industries: Large Language Models (LLMs) and Large Vision Models (LVMs). But are they really the same, or are there fundamental differences between them? In this talk, we will delve into the similarities and differences between these two powerful technologies. On the one hand, LLMs, like GPT, have revolutionized natural language processing, enabling advanced applications such as text generation, automatic translation, and language comprehension. On the other hand, LVMs are leading breakthroughs in computer vision, enhancing tasks such as image generation, object recognition, and semantic segmentation. We will discuss how both types of models work, the unique challenges they face, and how they can be applied in sectors such as education, medicine, art, film production, video game creation, and the creative industry.

Talk

No-Code AI with Vertex AutoML

Speakers: Mary Etokwudo

In this session, I’ll explain how Google’s AutoML lowers the technical barriers to entry for AI development. I’ll show practical examples of how developers, regardless of their AI experience level, can leverage these AutoML to build and deploy machine learning models. This session will cover the various stages of model development from data collection to model deployment.

Talk

Painless App Store publishing for Flutter iOS apps with Codemagic

Speakers: Kevin Suhajda

Learn how to build and publish your Flutter iOS apps to the App Store with Codemagic CI/CD.

Workshop

Prompt Injection Attacks: Understanding and Mitigating Risks in LLM-Powered Web Apps

Speakers: Jorrik Klijnsma

Dive into the wild world of prompt injection attacks in LLM-powered web apps! As AI chatbots and assistants become ubiquitous, a new breed of security vulnerabilities emerges. In this hands-on adventure, we'll dissect vulnerable chatbots, craft sneaky exploits, and explore robust defense strategies. Get ready to break (and fix) things as we create a simple LLM-powered app, then systematically exploit its weaknesses. You'll learn to identify common vulnerabilities, understand the anatomy of prompt injection attacks, and implement effective countermeasures. Perfect for devs who want to build safer AI-driven interfaces and stay ahead in the AI security game!

Talk

Web AI in 2024: Superpowers for modern web apps

Speakers: Jason Mayes

Web AI libraries and models crossed over 1 billion downloads in the last 2 years alone. If you're not yet using machine learning on the client side, now is the the time to see what's possible and the benefits it can bring your business over cloud based solutions such as lower costs, privacy for your end users, and low latency responses suitable for real-time applications. Learn what's new with the state of Web AI at Google and discover new generative AI models you can run client-side in the browser entirely offline along with key updates from Chrome, TensorFlow.js, MediaPipe, Core ML, Visual Blocks, and beyond. A must see talk for anyone working in the web space (or is using JavaScript) so you can bring your AI powered ideas to life faster than ever before.

Talk

Works in all browsers! Interoperability beyond availability

Speakers: Mariko Kosaka

Baseline gives you a snapshot of the web features supported by all browsers, but feature availability is only the first step in building the best, modern, capable web experience. This talk doesn't just list what's possible across browsers, it helps you figure out what's best for your product with the tools available today. Come and get answers to questions like: * How do you combine the features to create modern experiences like an adaptable, resilient, layout? What other modern UI patterns are now easy to implement? * Does updating your own implementation to the latest features make your code more maintainable and resilient? and more!

Talk