Skip to main content
T1 Large companies and unicorns Ant Group New grad Round 1

Ant Group AI Infra campus hiring first round

Real Ant Group AI Infra campus hiring first-round interview questions covering inference optimization and related topics

Inference optimization

Fundamentals

  1. Where does MLA (Multi-head Latent Attention) beat MHA?
  2. What problems can show up during weight absorption?
  3. What is an offline precompute scheme for KV Cache? For rarely used KV Cache, how do you offload and reload?
  4. Besides the methods above, what other KV Cache optimization tricks exist?

Project experience

  1. Deep dive into projects and internship experience.