From this track
Inside the Disaggregated Architecture Serving LLM Inference
Every LLM request is really two very different jobs. Reading your prompt (prefill) is compute-intensive, while generating the response token by token (decode) is dominated by memory bandwidth. For years, the industry ran both phases on the same hardware and accepted the compromise.
Architecting Nubank's Global Financial Infrastructure
Instant payment frameworks are transforming global finance, but few institutions have faced the infrastructure scale required by Brazil's Pix network.
How to Build a Real-Time Voice Agent
A voice agent looks like a chatbot with a microphone.
Rishabh Bhargava
Director of ML @Together AI
Live Resharding Without Regret: Lessons from Building Valkey's Atomic Slot Migration
Sharding is easy. Resharding under heavy load is notoriously difficult. How do you move gigabytes of state across live database nodes without dropping keys, blocking the main event loop, or breaking client abstractions?
Jacob Murphy
Open Source Maintainer @Valkey & Software Engineer @Google Cloud's Memorystore Team
