Interview Structure Overview Resume & Experience Review – The interviewer began by walking through my résumé, focusing on key projects and roles. – They asked for clarifications on timelines, responsibilities, and measurable outcomes (e.g., “Tell me about your ML project—what exact metrics improved?”). Machine Learning & Computer Vision Fundamentals – Questions targeted core concepts: bias–variance tradeoff, overfitting vs. underfitting, loss functions, and basic CV tasks. – Example prompts: “Explain how convolution works in a CNN,” or “How would you evaluate a classification model? What metrics would you choose?” PyTorch Deep Dive – They probed my hands-on experience: defining custom modules, managing data loaders, and writing a training loop from scratch. – Typical questions: “How do you implement dropout in PyTorch?” and “Walk me through backpropagation in your code—where does autograd come in?” DSA (Data Structures & Algorithms) Round – A live coding segment on a shared editor: classic problems (kernel pattern matching) and complexity analysis. – They evaluated my problem-solving approach: clarifying requirements, discussing edge cases, and optimizing time/space. Overall, the process flowed from high-level background to progressively deeper technical challenges—ending with a brief Q&A to address any remaining uncertainty