Leveraging Kubernetes for Scalable and Cost-Effective ML Serving on AWS

Explore a 51-minute technical talk from the Data Science Festival Oktoberfest 2024 where Rene-Jean Corneille, Director of Engineering at Onclusive, demonstrates how to build scalable and cost-effective machine learning serving infrastructure on AWS using Kubernetes. Learn about the strategic implementation of Kubernetes' self-healing properties, practical deployment steps, and solutions to common challenges in ML operations. Gain valuable insights into optimizing ML infrastructure while maintaining robust performance and minimizing operational costs. Designed for technical practitioners, discover actionable strategies for enhancing ML deployment through real-world examples and proven methodologies from Onclusive's engineering experience.