Authors: Vinay Kakade, Shiraz Zaman IntroductionIn a previous blog post, we discussed the architecture of Feature Service, which manages Machine Learning (ML) feature storage and access at Lyft. In this post, we’ll discuss the architecture of LyftLearn, a system built on Kubernetes, which manages ML model training as well as batch predictions. ML forms the backbone of the Lyft app and is used in d
![LyftLearn: ML Model Training Infrastructure built on Kubernetes](https://cdn-ak-scissors.b.st-hatena.com/image/square/7e75b0adea33eaed59848e92f7b1573657d14a32/height=288;version=1;width=512/https%3A%2F%2Fmiro.medium.com%2Fv2%2Fresize%3Afit%3A1200%2F1%2ApWfA3hanVmMKZkBHnmcxNw.png)