cold start

A static threshold on prompt length leaves money on the table both ways. The router that learns is a contextual bandit, and the interview lives in the reward function and the cold-start handling, not the algorithm name.

The GPU-platform capstone: dozens of models, spiky traffic, a fixed monthly GPU budget, and a p99 SLO that scale-to-zero would wreck. Token-based autoscaling, the three layers of LLM cold start, and the residency tiering that makes the budget math work.

A track lasts three minutes, a session lasts an hour, and a new song has zero plays the day it drops. The interview is about blending collaborative filtering with audio content embeddings, surviving cold start on both sides, and reading a skip as the loud negative it is.

This model's output is not a ranking, it is a price input. A miscalibrated CTR makes the auction bid wrong, so you overpay or underdeliver. Add conversions that land days after the click and advertisers with zero history, and calibration plus delayed feedback become the whole interview.

New courses launch every week and most browsers are signed-out or brand new, so the interesting half of this problem is what you recommend when you have almost no behavioral signal. The other half is not optimizing engagement into a clickbait catalog.