Design a logging serviceSystem designIngest logs from every service at terabytes per day, make them searchable within seconds, and keep them cheaply for months.
Last asked Aug 2026
Baseten system design interview
Round 4 of 5 · 2 questions reported
- 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 2
- Design an LLM inference serving platformAI systemDesign the system that serves several large models to many customers with low latency and high GPU utilization.