AI development cycles have a vast expanse of specific requirements and needs. Built with the right tools, a cloud-native computing platform on top of Kubernetes unleashes galactic possibilities to develop models quicker and easier than ever before. Join us for a celestial journey (with fun drawings) building an AI platform. At our mission’s end, we’ll discover a robust, scalable, secure platform ensuring stability, observability, and consistent UX via a web portal and self-service APIs.

At Bloomberg, we’ve been modularizing our Data Science Platform solar system with distinctive APIs (multi-cluster deployment, version control, debugging, resource management) that orbit together to efficiently manage and expose information.

We’ll use an ML inference platform to explore the cosmic realms of this implementation, using open source projects as guiding stars. We’ll provide guidance and ideas for other engineers to construct a stellar cloud-native platform and measure its universal success.