RepostedTikTok logo

TikTok · Onsite

In process

TikTok AI Infra Intern Kernel Round: 1 Experience

AI infrastructure engineer · InternshipMaster's degreeApr 2026
Shared by

A TikTok AI Infra intern onsite round 1 in April 2026 was all GPU depth: kernel fusion, Hopper warp specialization, MoE inference and RL routing collapse.

At a glance

  • Process: onsite round 1 in three blocks: kernel optimization, inference optimization, then project and internship deep dives (report 01).
  • Asked recently: custom CUDA or CuTe DSL kernels for fusion, when fusion slows things down, Hopper warp specialization, MoE expert specialization and routing collapse under RL, and AI agents that generate CUDA kernels (report 01, Apr 2026).
  • Difficulty: no coding problem; every question asked for hands-on experience with a concrete example.

Coverage: 1 report · AI Infrastructure Engineer intern · onsite round 1 · April 2026 · result pending when posted.

What came up

The round assumed real GPU kernel and MoE inference experience, and kept asking why an optimization helped or hurt.

Questions we found

GPU kernels and inference

Question Reports Last seen
Kernel-level work with CuTe DSL or custom CUDA kernels for fusion 1 Apr 2026
Which approach or framework for kernel fusion, and why 1 Apr 2026
When has kernel fusion made performance worse, and why? 1 Apr 2026
How does warp specialization on Hopper GPUs work? 1 Apr 2026
Without warp specialization but with tiling and shared memory, where is the loss? 1 Apr 2026
Optimizing MoE inference, especially with RL 1 Apr 2026
Has an MoE model really learned expert specialization? 1 Apr 2026
Routing collapse in RL + MoE training, and fixes 1 Apr 2026
Using an AI agent to generate CUDA kernels 1 Apr 2026

1 detailed candidate timeline

01: kernels, MoE inference and production serving

Interview date: April 2026 · Role: AI Infrastructure Engineer intern · Result: In process

Kernel optimization

  1. Experience with kernel-level optimization, such as CuTe DSL or custom CUDA kernels for operator fusion, with a specific example.
  2. Which approach or framework you would choose for kernel fusion, and why.
  3. Whether fusion ever made performance worse, and what caused it.
  4. How warp specialization works on NVIDIA Hopper GPUs, in hardware and software.
  5. If warp specialization is removed but tiling and shared memory stay, where the main performance loss comes from.

Inference optimization

  1. Hands-on MoE inference optimization, especially with reinforcement learning (RL).
  2. How to tell whether an MoE model has learned meaningful expert specialization rather than acting like a dense model split across experts.
  3. Routing collapse in RL + MoE training, where the reward pushes most tokens to a few experts, and how to fix it.

Projects and internship

  1. The most relevant project: challenges and contributions.
  2. The internship, especially optimization work on production inference services.
  3. Whether they had tried an AI agent that generates CUDA kernels automatically, and the approach.

Common questions

What GPU questions does TikTok ask AI Infra interns?

Kernel fusion and when it backfires, Hopper warp specialization, and what tiling and shared memory do without it (report 01).

Does the TikTok AI Infra intern round 1 have coding?

Not in this report: it was all kernel, MoE inference and project questions (report 01).

Keep practicing

Sources: Anywhere useful interview info can be found.

2 total reactions. Your reactions: none.
0 comments

Comments

0

No comments yet — be the first to share what you know.