IC Test is a critical part of semiconductor manufacturing and proper die binning has an important impact on the overall yield, product quality, process monitoring, and failure mode diagnostics. Edge analytics are becoming an increasingly important aspect of die disposition. By intercepting parts in real-time at wafer sort or final test, we can save downstream processing needs and improve product quality by predicting failures earlier, or before the parts are shipped. Furthermore, a complete MLOps platform to train, deploy, validate, and monitor a multitude of machine learning models across chip products is needed to achieve production worthiness. In this paper we will showcase a complete MLOps solution to realize improvement in identification and binning of failed parts compared to conventional statistical screening methods, among other use cases. We also show that by incorporating known cost data, we can automatically guide users to optimally tune the model for maximal failure capture with minimal overkill and realize significant business savings.