Speaker
Abstract
Delivering AI-powered features in mobile apps is not just about calling an LLM API. It is about crafting fast, reliable, and engaging user experiences. In this talk, I’ll share practical lessons from designing and scaling LLM-driven experiences in mobile apps, where frontend architecture and UX design played an important role.
We’ll explore how to architect for speed and interactivity, when to use on-device LLMs versus backend inference, and how to design interfaces that gracefully handle latency. We'll also examine the trade-offs that shape responsive, cost-effective, and scalable AI features.
Whether you're experimenting with LLMs in your product or already in production, you’ll leave with insights to make your AI-powered experiences feel fast, native, and user-first.
Topics
QCon San Francisco 2025 is a three day conference for senior software engineers, architects and team leads. An international program committee of working engineers selects every session. Patterns and practices, not products and pitches.
From the same track
Tuesday 18 November
10:35 Pacific DEKJ Session Lessons Learned in Migrating to Micro-Frontends Luca Mezzalira Director of 50 Cents Media | Former AWS & DAZN | QCon Cohorts Facilitator | O'Reilly Author | International Speaker | Architecture Storyteller Migrating to a micro-frontend architecture promises scalability, faster development cycles, and autonomous teams—but the journey is rarely straightforward. 11:45 Seacliff ABC Session Building and Scaling UI Systems for Internal Tools at Meta Cindy Zhang Front End Engineer, InfraX @Meta Meta’s internal tools empower the company to operate efficiently, enabling the creation of unique, tailored solutions that fit evolving business needs. 13:35 Seacliff ABC Session Platform Engineering From VR to Flat Screens: Bridging the Input and Immersion Gap Dany Lepage VP of Technology @Lucky VR - Building Virtual Vegas, xUbisoft, xFramestore, xNvidia Expanding the market of your VR game to other platforms may seem like an easy way to increase your revenues but the journey is all but simple. When what makes your game unique is the presence and immersion it provides, reproducing the experience on a flat screen is a daunting task. 14:45 Pacific DEKJ Session Machine Learning Designing Fast, Delightful UX With LLMs for Mobile Frontends Balakrishnan (Bala) Ramdoss Senior Android Engineer @Amazon - Building Camera-Based AI Features, Specializes in Scalable Solutions for Complex Challenges Delivering AI-powered features in mobile apps is not just about calling an LLM API. It is about crafting fast, reliable, and engaging user experiences. 15:55 Seacliff D Unconference Unconference: Innovations in Front-End 17:05 Pacific DEKJ Session Realtime Why Fetch When You Can Sync? Building Local-First Apps on a Sync Engine Architecture James Arthur Co-founder and CEO @ElectricSQL, Previously Co-Founder and CTO @Hazy and @Opendesk Front-end has long been about reactivity frameworks and client-side state management. However, the alpha in these is receding.