Microsoft·Machine Learning Engineer·Technical Phone Screen
- You have an LLM training dataset where each example has a prompt, an Excel table, and a model response. Implement a quality checker that flags bad examples. Think about: is the prompt non-empty and well-formed, is the table parseable and within size limits, does the response reference columns and rows that actually exist, does the response format match what the prompt asked for, and is there basic consistency between prompt intent and response?
- Given a pretrained model from HuggingFace, walk through how you'd decide whether finetuning is actually necessary for these table-grounded tasks. What criteria matter, and if you do finetune, what approach would you pick between LoRA, full supervised finetuning, or instruction tuning?
“This took me a while to fully scope.”