Machine Learning System Design Interview, issue 45, Jun 2, 2026
The Temporal Blindness Trap
Senior ML Engineer interview at Netflix, and the interviewer asks:
“You’re serving recommendations from a batch pipeline that precomputes results nightly. Engagement is dropping and users say the recs feel stale. Walk me through the real failure mode, and when batch stops being the right call.”
Don’t say: “We should retrain the model more often.”
Your batch pipeline isn't wrong, it's frozen in time, paying for compute savings with engagement decay that never shows up on your cloud bill.
The full answer, with the mechanism and the arithmetic, is for paid subscribers on Substack.