< session />

Powering Generative AI with Kubernetes: A Cloud-Native Approach

Thu, 25 April

The explosion of interest in Generative AI has brought to light the critical need for scalable and reliable infrastructure to support these advanced technologies. Foundational models driving generative AI, particularly those used in commercial platforms like OpenAI, rely heavily on Kubernetes for model serving and inference endpoints.

This session delves into the practical aspects of deploying open-source generative AI models and applications within a Kubernetes and cloud-native framework. A key focus will be on how enterprises can establish end-to-end pipelines to develop context-rich, Large Language Model (LLM)-based applications in-house. This approach is particularly beneficial for handling sensitive data securely, without the need to rely on external endpoints.

Designed for those seeking to understand the intersection of modern AI and cloud-native technology, this hands-on session will share insights and best practices for running cutting-edge AI applications on Kubernetes. Attendees will leave with a deeper understanding of how to harness the power of Kubernetes to optimize their generative AI projects.

< speaker_info />

About the speaker

Janakiram MSV

Principal Analyst, Janakiram & Associates

Janakiram MSV (Jani) is a practicing architect, research analyst, and advisor to Silicon Valley startups. He focuses on the convergence of modern infrastructure powered by Kubernetes and machine intelligence driven by IoT, Edge, and AI. Before becoming an entrepreneur, he spent over a decade as a product manager and technology evangelist at Microsoft Corporation and Amazon Web Services. Janakiram regularly writes for Forbes, InfoWorld, and The New Stack, covering the latest from the technology industry. He is a keynote speaker for internal sales conferences, product launches, and user conferences hosted by technology companies of all sizes.