Eric Johnson is a Principal Developer Advocate for Serverless Applications at Amazon Web Services and is based in Northern Colorado. Eric is a fanatic about serverless and enjoys helping developers understand how serverless technologies introduce a major paradigm shift in how they approach building and running applications at a massive scale with minimal administration overhead. Prior to this, Eric has worked as a developer, solutions architect and AWS Evangelist for an AWS partner company.
Operating ML Inference at Scale With Serverless
Companies are scrambling to take advantage of Machine Learning (ML). From fraud detection to sentiment analysis, everyday ML is helping businesses make critical decisions. However, the operational overhead of the compute required to support ML workloads can be large, costly, and complex. In deep learning applications, inference can drive as much as 90% of computing costs.
In this session, Eric will show how to reduce cost and management overhead by moving ML inference to a serverless architecture. He will demonstrate building and deploying an ML inference project on serverless with infrastructure as code (IaC). Finally, Eric will discuss optimizing serverless compute for specific workloads and how to use cloud-native AI/ML services when possible.
At the end of this session, whether you’re a developer or a data scientist, you will have a basic understanding of how to create and deploy an inference engine using serverless technologies.