NVIDIA ML & AI interview questions.
Questions in the CrackML corpus associated with NVIDIA. Use company evidence as a prioritization signal, not a promise that an exact question will repeat.
Serialize and Deserialize Binary TreePython & DSA · hard · Evidence 80/100How would you profile GPU inference latency end to end?ML System Design · hard · Evidence 41/100How do throughput and tail latency trade off in model serving?ML System Design · hard · Evidence 41/100How do continuous batching and paged attention improve LLM serving?GenAI & LLM · hard · Evidence 41/100How would you debug unexpectedly low GPU utilization during inference?ML System Design · hard · Evidence 41/100Explain the architecture of an LLM serving stack built around vLLM.GenAI & LLM · hard · Evidence 41/100How would you reduce memory movement in a custom CUDA inference kernel?ML Coding & PyTorch · hard · Evidence 41/100What bottlenecks would you optimize in a CUDA kernel used for model inference?ML Coding & PyTorch · hard · Evidence 41/100How would you optimize a deep-learning operation for GPU execution?ML Coding & PyTorch · hard · Evidence 40/100How do CPU and GPU architecture change ML data movement?ML Coding & PyTorch · hard · Evidence 40/100How would you quantize a neural network for faster inference?GenAI & LLM · medium · Evidence 40/100