As new machine learning (ML) techniques continue to advance and provide the promise of better performance, platform teams everywhere are trying to adapt to support increasingly complex models. While many models served at Etsy still use "classic" model architectures (such as gradient-boosted trees), there has been a large shift and preference for deep learning techniques. The decision for the Search Ranking (SR) team to use deep learning in particular necessitated advances in ML Platform capabilities. In this post, we'll go over the workload-tuning and observability capabilities we created to combat the challenges serving deep learning ranking at scale within Etsy. Ranking use cases tend to be trickier to serve at low latency and low cost relative to other ML use cases.