AI has been a hot topic lately, with advances being made constantly in what is possible, there has not been as much discussion of the infrastructure and scaling challenges that come with it. How do you support dozens of different languages and frameworks, and make them interoperate invisibly? How do you scale to run abstract code from thousands of different developers, simultaneously and elastically, while maintaining less than 15ms of overhead? At Algorithmia, we’ve built, deployed, and scaled thousands of algorithms and machine learning models, using every kind of framework (from scikit-learn to tensorflow). 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.
High impact blog posts and eBooks on API business models, and tech advice
Connect with market leading platform creators at our events
Join a helpful community of API practitioners
Can't make it to the event? Signup to the Nordic APIs newsletter for quality content. High
impact blog posts on API business models and tech advice.
Become a part of the world’s largest community of API practitioners and enthusiasts. Share your insights on the blog, speak at an event or exhibit at our conferences and create new business relationships with decision makers and top influencers responsible for API solutions.