Production ML
-
Evaluation Pipeline Design: What CI Evals Miss
CI evals catch regressions in code. They don't catch production drift, prompt sensitivity, or behavioural change in the upstream models you depend on.
-
Online Inference Latency: Where the Budget Actually Goes
P99 latency is a product problem as much as an engineering one. Breaking down the inference budget: model compute, preprocessing, retrieval and network.
-
Feature Store Comparison 2026: Feast, Tecton, and Hopsworks
Feature stores are table stakes for production ML. Feast, Tecton, Hopsworks, and the cloud-native options compared on freshness, scale, and team bandwidth.