Nvidia | Deep Learning Software Engineering Intern | Coding + Trivia | Phone Screen

This one had one coding question and some trivia questions Coding: Multi Head Attention in PyTorch Implement multi head self attention in PyTorch using basic tensor operations. The implementation should: Project inputs into Q, K, V Reshape tensors to support multiple heads Compute scaled dot product attention Apply softmax and combine values Project the concatenated output back to the model dimension Fused QK and Nor...