A model scores well offline and performs badly in production. What infrastructure causes would you check first?

Before blaming the model, check whether it is being fed the same thing it was trained on. Most of the gap is a pipeline difference, and pipeline differences are a platform problem with a platform fix.

Grounded in researched DevOps, SRE and platform engineering interview loops, written to a senior-engineer editorial bar, and never padded to hit a word count.