Joshua Arvin Lat

More companies over the past few months have started building their own generative AI-powered applications and systems. While some organizations have the capacity, capability, and the budget to set up their own LLM's in-house, other organizations may opt to a more practical and scalable approach. In this session, we'll dive deep into various strategies, techniques, and best practices when building and managing serverless Generative AI applications. This includes setting up a truly serverless RAG-powered Generative AI application as well as making sure that the overall cost of the project does not exceed the allocated budget. At the end of this session, technical professionals would have a better idea on how to pragmatically build and maintain these types of applications and systems.