Your question is Transformer Fundamentals. Take a moment with it on the right.
Talk me through your thinking if you like. When you're confident, submit your answer and I'll grade it like a real screen (7/10 or better passes).
What is a Transformer and how does it work?
Explain the roles of tokenization, embeddings, positional encoding, self-attention, feed-forward layers, residual connections, and layer normalization. Include a concise Python example using Hugging Face Transformers that fine-tunes a pretrained encoder for text classification and briefly explain how training and inference differ.