Real-time Machine Learning Applications at Gigascale

Machine Learning is disrupting nearly every industry. AI-First is the new mantra for many, but how do you architect, develop and manage intelligent, real-time applications incorporating Machine Learning that can scale to handle modern workloads driven by Cloud and Edge?
In this talk, you will learn the most critical elements for achieving machine learning applications that can scale to any throughput or volume of interaction up to one billion events per second or more. Also covered will be how to integrate these applications with MLOps frameworks, and how to design for zero-downtime architectures as well as global scale multi-region.