Designing Fast, Delightful UX With LLMs for Mobile Frontends (QCon presentation)
At QCon San Francisco, Amazon senior engineer Balakrishnan Ramdoss presented techniques for architecting production-grade conversational mobile apps with LLMs, discussing model latency mitigation, server-driven UI and Backend-for-Frontend patterns, prompt optimization for UI selection, and options for low-latency, privacy-first on-device AI integration.