Ime Archibong, head of New Product Experimentation (NPE) at Meta, and 12-year Meta veteran will talk about 0-1 innovation, at scale. He’ll discuss the value of experimentation as an approach, and demystify how real breakthroughs happen.

There are many tools that Creators can use to build novel AR experiences. However not many of these tools can deliver a wide ranging set of capabilities and creative assets to billions of devices with both quality and speed. In this talk we present Meta's experience building a large scale AR Runtime and share the lessons we learned along the way.

NVIDIA Map aggregates data from millions of NVIDIA DRIVE Hyperion consumer and survey data-collection vehicles for safe, reliable, and up-to-date global high-def map coverage. The platform supports automated driving functionality from L2+ to Level 4 autonomous vehicles. It also takes advantage of a fully automated mapping pipeline that implements machine learning and deep learning to create, update, and validate HD maps with no human intervention. This talk focuses on the challenges of building performant systems that can handle large-scale geospatial sensor data and deliver real-time updates to maps.

As a mobile app grows in users, features, and contributing engineers, there are often tradeoffs between the performance of the app and the velocity of feature growth. Messenger's users have high performance expectations, so we've had to redefine the way we write mobile infrastructure to maintain that performance while still providing reasonable developer velocity. This talk will dive into some of the approaches the Messenger team has taken, like optimizing our use of SQLite, carefully choosing when we load different parts of the application, and modularizing our dependencies.

In this talk, I'll be providing an overview of how we use ML algorithms to detect policy violative content on YouTube across all entity types: videos, comments, livestreams, engagements, etc and keep our community safe. ML algorithms are an essential part of YouTube Trust and Safety and I'm excited to share the lessons that we learned over many years while building, deploying and maintaining models at scale. Furthemore, I'll be covering the unique sets of challenges for different entity types and product surfaces, like livestreams and shorts, which makes the problem domain particularly intriguing.

An overview of how WhatsApp thinks of privacy in the messaging world. We’ll go through some of our general principles, concrete product use cases, and challenges that come with privacy at scale.

Trust & Safety at Twitch is uniquely challenging, as the vast majority of content and chat interactions unfold in real time, across a wide variety of communities with different needs, cultures, and audiences. Mitigating and preventing harm means creating fast-acting models that react quickly to bad actors’ new attack vectors, while giving Creators control over their communities. We need fast-acting models to prevent harm early and scale to all of our traffic, which can be thousands of Requests per Second. In this talk we highlight one specific challenge—channel-level ban evasion—and discuss how we address ML modeling and engineering challenges and fight this behavior on our service. We will touch on a number of strategies, including the Twitch ML Infra & ML Ops ecosystem, and how we build a complete ML stack from pipelining through real-time features, model serving, feature store and other systems.

Moderated by Sara Wong

Building successful products is hard. Building successful products at scale? Ridiculously hard! It takes strong vision, deep dedication, consistent execution, with a healthy sprinkle of unorthodox methods. This talk shares a few helpful lessons derived from decades of experience, to aid the modern product development process.

We’ll talk about two 0-1 products in the creator space: Subscriptions and Music Releases on IG. We’ll walk through how we built the early stages of these as visually stunning products, as well as the unique set of challenges our teams will solve for scaling them within the IG ecosystem of billions of users. Some of the challenges include keeping simplicity as we add features, ensuring portability, keeping a high bar for integrity, expanding products to different geographies, and scaling product infrastructure to handle larger loads.

In 2007, Facebook released their first iOS App. It was written in HTML, and it was supported by a single engineer. Since then, the Facebook iOS App has grown into a native ‘platform’ which supports more than 100 products, and hundreds of engineers. This talk focuses on the incremental changes made to Facebook’s App Architecture so it could sustainably support the hundreds of engineers who work on it, while still embracing Meta’s ‘move fast’ mentality.

At Capital One, building beautiful, rich, and performant mobile applications for iOS and Android is essential to providing a best-in-class experience for our customers and delivering on our mission to change banking for good. However, as our applications have grown in both size and scope — and the number of developers contributing to our codebases has increased — we’ve encountered numerous challenges, including long build times, duplicated code, highly coupled dependencies, and limitations of our dev tooling. In this presentation, we’ll discuss in detail the investments in our mobile platform that we’ve made over the years to conquer these obstacles, and our approach to repository management, application architecture, programming patterns, and test automation that empowers our mobile developers to deliver great customer experiences at scale.