Skip to main content
T0 Big tech Alibaba Round 1

Alibaba AI Infra first round (1)

Real Alibaba AI Infra first-round interview questions covering AI Infra and related topics

Fundamentals

  1. What motivates Group Query Attention, and what does it do?
  2. In MoE, is expert routing per token or per sequence?
  3. Common KV Cache optimization strategies?
  4. How can the retrieval module in a RAG system be implemented?
  5. Common data-cleaning methods in pretraining?

Project experience

  1. Explain the overall architecture of the Agent system you designed.

Coding

  1. Implement an LRU Cache.