Together AI system design interview

Round 6 of 7

See the whole loop
Length
60 min
Format
Design discussion
They grade
Throughput versus latency, GPU memory bandwidth, distributed execution
Heads-up
Mainly for senior candidates. Prompts: serving 100+ open models to many tenants, a fine-tuning service that manages LoRA adapters.

Questions

No Together AI reports yet. Other labs ask: