Apple AI Infrastructure Engineer interview questions

Trace a grid into blocks and warps, then distinguish resident work from ready work. Derive an occupancy limit without treating it as a speed target.

Count gradient traffic from a named dtype, separate initialization and buffer broadcasts, and measure the reduction tail instead of assuming it is hidden.

Follow the weight bytes through a small decode batch and a long prefill. A scoped roofline calculation explains the difference without pretending to predict actual latency.

Count two matrix shapes to derive the H100 ridge, throughput ceilings and time floors. Compare an illustrative measurement with its bound before deciding what to optimize.

Choose between supported InfiniBand and RoCE designs using workload tests, congestion behavior and a complete cost model.

Separate storage scope from physical backing, then follow a warp through adjacent and strided loads. Count useful bytes and requested sectors before inferring HBM traffic or speed.

Follow a token into retained attention state, derive bytes per position for a 70B model, and distinguish present cache usage from the room needed to finish a response.

Trace one cache position through a block table, calculate the memory recovered from oversized reservations, and explain why sharing still needs careful writes and matching.

Work from token timestamps to first-token wait, average pace and individual stalls. Then count requests meeting both latency limits, keeping failures and measurement boundaries explicit.

Work from each GPU's cache budget, reserve room for generated tokens, then check latency separately. A limiting-rank example shows why fitting today's prompts is not enough to admit tomorrow's work.

Compare useful parallel work, data movement and reuse. A synthetic CPU/GPU crossover shows why a faster kernel can still lose the end-to-end request.

Derive the weight-only shortcut, then add KV traffic and feasible eight-GPU placement. A worked latency floor shows why batch size alone cannot establish the decode bottleneck.

Separate weight storage, matrix arithmetic and attention-cache precision. Choose a supported candidate using task quality, memory and service measurements.

Use proportional bit layouts and adjacent values around one to distinguish range from precision. Then choose formats from numerical tests and actual kernel support.

Filter engine candidates by exact compatibility, then compare correctness, goodput and operational cost on the same workload.

Implement priority admission and completion, preserve a preempted job’s sequence, and distinguish a sufficient greedy victim set from an optimal one.