Baseten system design interview

Round 4 of 5 · 1 question reported

See the whole loop
Length
60 min
Format
Design discussion
They grade
Model serving, latency and GPU scaling
Heads-up
Reported prompts: serving an LLM under bursty traffic, tracking down a p99 latency spike.

Questions Baseten asks in this round 1

About the Baseten system design round

What does Baseten ask in the system design round?

The most asked: Design an LLM inference serving platform.

How long is the Baseten system design round?

About 60 minutes.

What is the Baseten system design round like?

Design discussion. They grade: Model serving, latency and GPU scaling.