Machine Learning System Design Interview, issue 26, May 14, 2026

The Inference Bottleneck Illusion

Senior ML Engineer interview at Meta, and the interviewer asks:

You’ve built a two-tower recommendation system balancing high recall and high precision. The problem? It takes 400ms to run the pipeline, but product demands a strict 100ms SLA. Where do you cut latency without destroying the user experience?

Why obsessing over model compression silently ignores your true RecSys latency killer, and how attacking network I/O and feature fetching actually hits your strict 100ms SLA.

The full answer, with the mechanism and the arithmetic, is for paid subscribers on Substack.

Read it on Substack

Get the next one

Free on Substack. Unsubscribe in one click.