System Design AI

Guided practice

Start with a template. Work through each step. Ask Coach when you need a second opinion.

Designs with worked examples 1

Ordered by design number

Company tags are community-reported. Counts on cards show how many people reported that design.

GPUsClear filters

105. Design a Distributed Training Platform
Train 1 B to 400 B models on 8 to 10,240 H100s: DDP, ZeRO and FSDP, tensor and pipeline parallel over NVLink and EFA, checkpoints, hot spares, MFU and goodput.
ClassicMedium
Machine learning AI infrastructure AWS
+3
GPUs Parallelism Training
Worked design
Practice

Self-paced by default. Your answers and canvas stay private. AI feedback runs only when you ask for it.