Skip to content

Cloud & AI Infrastructure

Building & scaling custom serverless AI

with Panley Cooze

Thursday 9 July 15:00 – 17:00 Room M6 (40 Seats)

About This Session

When building custom AI solutions, you often have to rent a GPU 24/7. But that doesn't have to be the case, in this workshop you will learn how to build a custom LLM on Runpod that scales with your users, without paying for off hours. Within just an hour, you will have a production-ready LLM endpoint and a deeper understanding of the Runpod platform!

Topics

  • AI Models
  • Best Practices
  • Containers
  • Generative AI (GenAI)
  • Load Balancing
  • Scaling