Jun 6, 2018
6:00PM - 8:00PM
A group for anyone interested in building web, mobile and Internet-of-Things applications with serverless architectures using the Serverless Framework and more! We’ll focus heavily on Amazon Web Services and discuss AWS Lambda as the focal point of AWS.
• 6:00 pm – Gathering and Networking
• 6:30 pm – Opening
• 6:45 pm – The Operating System for AI: How Microservices and Serverless Computing Enable the Next Generation of Machine Intelligence, by Jonathan Peck, Algorithmia
• 7:15 pm – Logging and Debugging at Scale, by Chris Robertson, Scalyr
• 7:45 pm – Closing
The Operating System for AI: How Microservices and Serverless Computing Enable the Next Generation of Machine Intelligence, by Jonathan Peck, Algorithmia
You’ve trained machine learning models on your data, but how do you put them into production? When you have thousands of model versions, each written in any mix of frameworks (R/Java/Ruby/SciKit/Caffe/Tensorflow on GPUs etc), how do you efficiently deploy them as elastic, scalable, secure APIs with 10ms of latency?
ML has been advancing rapidly, but only a few contributors are focusing on the infrastructure and scaling challenges that come with it. We’ve built, deployed, and scaled thousands of algorithms and machine learning models, using every kind of framework. We’ve seen many of the challenges faced in this area, and in this talk I’ll share some insights into the problems you’re likely to face, and how to approach solving them.
In brief, we’ll examine the need for, and implementations of, a complete “Operating System for AI”: a common interface for different algorithms to be used and combined, and a general architecture for serverless machine learning which is discoverable, versioned, scalable and sharable.
Logging and Debugging at Scale,, by Chris Robertson, Scalyr
Shifting from a traditional server-centric application deployment model to either Lambda/Serverless or abstracted containers requires reassessing how Operations teams (or the developers tasked with Ops responsibilities), monitor, debug, and support production code. Often times the abstractions that help developers rapidly deploy code also make it harder to understand root causes when things go wrong. We’ll go into common issues and, more importantly, tools to solve them.