#latency

Design large-scale model inference serving with back-of-envelope sizing
AI systemWaymo
▲ 00 solutions
Design a real-time AI voice agent
AI systemDecagon
▲ 00 solutions
Check and insert among a million user IDs
System designMercor
▲ 00 solutions
Fast expensive tokens versus slow cheap tokens
AI systemGoogle
▲ 00 solutions
Resize a hash map without long pauses
CodingApple
▲ 00 solutions
Design an answer engine with citations
AI systemHardPerplexity
▲ 01 solution