1. What are the evaluation metrics used for LLM evaluation? 2. How is LSTM different from Transformer architecture? 3. Why is RAG architecture used instead of fine-tuning LLM models? 4. How is BERT different from GPT model? 5. What will I do in case of imbalanced dataset? 6. How is linear regression different from logistic regression? What types of loss functions are used in each of these scenarios? 7. What is the task of dropout and activation function?
Something related to Leadership principle
How did you apply amazon leadership principles when faced with a problem in your experience?
What are the techniques would you use so that the graph-CNNs scale well?
Q: What is the difference between bagging and boosting? Q: Explain K-means. etc.
Tell me about a time you had a strict deadline and how you handled the situation.
How to build a recommender system from product description. What is SGD and why and when does it work, and how to improve.
Typical leetcode questions. Even the recruiters advised me to "practice" on leetcode before the interviews. Total waste of time ML depth round was not a depth round at all. Interviewer was busy taking notes and didn't probe the concepts further "Name all the hyperparameters of boosting model - XGB and/or GBM" Simpler alternative is to replace all interviewers with automated tests. I felt like I was talking to computers. I prefer leetcoding and attending multiple choice ML questions over talking to people who mechanistically follow instructions
How would you represent simple arithmetic as a computer program?
Describe an occasion where you completed a task out of your comfort zone.
Viewing 461 - 470 interview questions