Hard

Design an LLM Inference Performance Optimization Program System Design Interview

Design the measurement, kernel, rollout, and correctness system that closes the gap between theoretical and achieved inference throughput.

1. Problem Statement

Your inference fleet is 35 percent below expected throughput and p99 latency regressed after a runtime update. Design the system and process to diagnose and safely improve it.

2. Architecture Discussion Map

Use this as one discussion aid, not a single correct answer. Your design should follow from the requirements, scale, and trade-offs you establish.

Rendering architecture diagram...
Mermaid Source (For AI Bots)
graph LR
    A["Design an LLM Inference Performance Optimization Program"]
    A --> F1["Cross-layer latency and throughput attribution"]
    A --> F2["Roofline analysis and representative benchmarks"]
    A --> F3["Kernel fusion, memory bandwidth, and variable sequence lengths"]
    A --> F4["Quantization and numerical correctness"]
    A --> F5["Canary rollout, regression detection, and rollback"]

3. Key Focus Areas

  • 1
    Cross-layer latency and throughput attribution
  • 2
    Roofline analysis and representative benchmarks
  • 3
    Kernel fusion, memory bandwidth, and variable sequence lengths
  • 4
    Quantization and numerical correctness
  • 5
    Canary rollout, regression detection, and rollback

4. What Strong Candidates Should Demonstrate

  • Trace latency across routing, batching, runtime, kernels, memory, and hardware.
  • Use roofline and FLOPs funnels rather than isolated microbenchmarks.
  • Treat output correctness as a release gate for optimization.

Want interactive feedback?

Practice drawing this system component-by-component on a live whiteboard while the interviewer probes at your target level.

Continue to Dashboard

Core Concepts

CUDARoofline AnalysisKernel FusionQuantizationPerformance Evals

Continue preparing

Build a complete software engineer mock interview plan

Use this scenario in a focused preparation plan

Related System Design

Design a Shared GPU Cluster Scheduler

Design scheduling and capacity management for training, research, and production inference on a large heterogeneous accelerator fleet.