Engineering Cloud Native AI Platform

Explore best practices and challenges in building large-scale, efficient, and reliable AI/ML platforms using cloud-native technologies in this 13-minute conference talk. Delve into the complexities of designing data science and ML applications amidst the diverse landscape of ML frameworks, hardware accelerators, and cloud vendors. Learn about the intricacies of creating inference systems for models of varying sizes, including Large Language Models (LLMs). Gain insights into leveraging cloud-native technologies such as Kubernetes, Kubeflow, and KServe to construct robust AI/ML platforms. Examine a reference platform dedicated to modern cloud-native AI infrastructure, providing valuable knowledge for engineers and data scientists working on cutting-edge AI projects.