Explain the Bias-Variance trade-off. How does it affect model performance? What is cross-validation and why is it important? Describe a few different types of cross-validation techniques. Can you explain the differences between supervised, unsupervised, and semi-supervised learning? Provide examples of each. What is regularization and why is it used in machine learning? Explain the difference between L1 and L2 regularization. Walk me through the process of feature selection. What techniques can be used to identify important features? How would you handle missing data in a dataset? What are some common imputation techniques? Describe the steps involved in a typical natural language processing (NLP) pipeline. What are some methods for reducing dimensionality in a dataset? How do these methods work? Explain the concept of overfitting. How can it be identified and mitigated? Discuss the differences between precision, recall, and F1-score. When would you prioritize one over the others? What is the Curse of Dimensionality? How does it impact the performance of machine learning algorithms? Can you explain the k-nearest neighbors (KNN) algorithm? How do you determine the value of 'k'?

Applied for Amazon AGI. After first round, it will go into full round of multiple interviews. Lots of modern LLM training technic questions. There are still some behavioral questions, but less than general Amazon roles.