What we're about
Upcoming events (1)
Find out about other upcoming online meetups and recordings from past Kafka Meetups all over the world: cnfl.io/meetup-hub
*Time below in Central time - to find out when the event is in your timezone follow this link: http://www.worldtimebuddy.com/event?lid=6%2C100%2C8&h=100&sts=26912160&sln=22-23&a=show
4:00pm-4:05pm: Online Networking
4:05pm-4:50pm: Lai Wei, AWS + Stanislav Kirdey, Netflix (Q&A included)
4:50pm: Log in or Join our Forum (forum.confluent.io) to ask any follow up questions!
Speakers: Lai Wei, AWS + Stanislav Kirdey, Netflix
Talk: Using DJL to deploy a pre-trained deep learning model directly from Apache Kafka®
Abstract: Leading streaming users such as Netflix and Amazon music use open source library DJL to deploy deep learning models directly from Scala-based streaming applications. Deep Java Library (djl) is an open source library designed to let you build and deploy AI models within the Java/Scala ecosystem. In this talk, we will give a high-level overview of DJL architecture and main features. Then we will show how data engineers with minimum data science experience can make use of the latest and greatest open source AI models by using DJL to deploy a pre-trained deep learning model directly from Kafka. We can end with a customer story (Netflix) on deploying pre-trained deep learning models from streaming applications for real-time and large scale inference.
Lai Wei is a Software Engineer with AWS Deep Learning team. He is focusing on building easy to use, high-performance and scalable deep learning frameworks for engineers and data scientists. Outside of work, he enjoys spending time with his son, hiking, and skiing.
Stanislav Kirdey works at Netflix where he focuses on large-scale, applied machine learning in the areas of NLP, search, and anomaly detection. Outside of machine learning and work, Stanislav is obsessed with RuPaul’s Drag Race, POSE, and Star Trek.
Online Meetup Etiquette:
•Please unmute yourself when you have a question.
•Please hold your questions until the end of the presentation or use the zoomchat!
•Please arrive on time as zoom meetings can become locked for many reasons (though if you get locked out a recording will be available, but you may have to wait a little while for it!
If you would like to speak or host our next event please let us know! [masked]