Deep learning achieves great performance in many areas, and it’s especially useful for computer vision tasks. However, using deep learning in production is challenging: it requires a lot of effort for developing and running the infrastructure to serve deep learning models at scale. In this talk, we present a system for classifying images on one of the largest online classified advertising platforms. The main requirement for this system is to classify tens of millions of images daily and be able to operate reliably even during peak hours. It took a year and lots of trial and error to arrive at the system we currently use. We present the details of this journey and tell our story: how we approached it initially, what worked and what didn’t, how it evolved and how it’s working right now. Of course, we also walk you through the technical details and show how to implement a similar system using Python, AWS, Kubernetes, MXNet, and TensorFlow.