Inference architecture with SageMaker for your Machine Learning SaaS

Join us for our upcoming Virtual Meetup on “Inference architecture with SageMaker for your Machine Learning SaaS”, led by Joshua Fox - Senior Cloud Architect at DoiT International and Michael Pelts - Sr. Solutions Architect at AWS.

If you are running a Machine Learning service that supports multiple business customers, you need to keep their data and invocations separate from each other. We’ll show you a few ways to do it — “silo”, “pool”, and “bridge” with tradeoffs of isolation vs flexible scalability.

Hope to see you lot on the next session!