efficiency

Both are conditional compute, but one scales parameters and the other scales depth. The signal is knowing which axis each routes along and why that changes the FLOP story. Here is the sharp version.

Distillation buys you most of a frontier model's quality at a fraction of the serving cost. The signal is naming the three LLM-specific variants and knowing which one works against a closed API. Here is the answer.

One trained embedding you can truncate to any length and still use. The signal is the nested-prefix training objective and the coarse-to-fine retrieval win it unlocks at scale. Here is the answer.

nvidia-smi showing 100% can hide that you are using a fraction of the hardware's real compute. The signal is MFU (useful FLOPs vs peak) and the gap between 'the GPU is busy' and 'the GPU is efficient'.

Hosting one full fine-tuned model per customer scales linearly in GPUs and bankrupts you fast. There is a way to put hundreds of variants on one GPU without giving up batching. The interviewer wants to hear how.