Breadth - generative models, loss functions, tokenizers, LLMs, convolutions, residuals Depth - my research, applications and relation to other fields Math - implement SGD for a problem (derive gradients, update, momentum etc.). Derive closed-form solution to this problem.
Describe some criterion for model selection? Why is dimension reduction important?
You could be asked to describe one of your previous projects, answer behavioral questions, and implement an algorithm from scratch.
For the technical portion, was asked how to design a dictionary from scratch without using a dictionary. Discussed options such as storing data in a fixed array, or sorting into a list. The best solution uses a hashmap and open addressing to handle possible collisions.
1. Formulas of cost functions
Any difference between transformer architecture and that of LLM
1) Scenarios: How do you use your knowledge of AI/ML to help Zalando solve problem Z? 2) Greatest achievement? Biggest failure? How do you manage conflict? 3) Leetcode medium tasks.
Just completed 1st round, waiting for results.
Explain one of your recent projects.
basic linear regression transformer attention
Viewing 271 - 280 interview questions