Why does naive Kubernetes GPU scheduling strand GPUs, and how would you serve thousands of models cheaply?
The cluster shows eight free GPUs and your four-GPU pod still won't schedule, the fragmentation puzzle GPU-platform rounds open with. Bin-packing vs. spreading, MIG/MPS/time-slicing for the small-model problem, and the pod-per-model math that breaks at scale.
Updated Aug 2026 · Grounded in real Forward Deployed Engineer interview loops and written to a senior-engineer editorial bar.
The cluster shows eight free GPUs and your four-GPU pod still won't schedule, the fragmentation puzzle GPU-platform rounds open with. Bin-packing vs. spreading, MIG/MPS/time-slicing for the small-model problem, and the pod-per-model math that breaks at scale.
Lead with where the obvious approach breaks, because that is the judgment they are screening for — most candidates jump straight to the happy path and lose the room.
Then walk the failure back through the pipeline in order, naming the one metric the customer's exec sponsor actually cares about before you propose the fix.
