R1: Asked to describe Coactive, followed by technical questions on logistic regression, confidence intervals, model deployment, and representation encoding in CLIP etc.. R2: Focused primarily on my projects. R3: Specific questions related to my technical talk.
Describe yourself in 3 words
Build a news feed for TR.
(1) Talk about your research. (2) A design question on labeling the multiple products from pictures taken by the phone. (3) Coding: Range sum query 2d - immutable
Many Machine Learning related questions and a code exercise of sorting elements in a string and counting most frequent tokens.
The OA was just standard leetcode questions
Discuss ideas for improving the performance of a machine translation system. Followup, how would you decide whether you succeeded?
1. reverse string in-place 2. find maximum number using list of numbers
Leetcode Coding question from top frequency problems
Problem: Top K Most Similar Documents You are given: an integer array queryEmb of length D, representing a query embedding a 2D integer array docEmbs of size N x D, representing N document embeddings an integer k All embeddings are already L2-normalized. The cosine similarity between two normalized vectors is equal to their dot product. Return the indices of the k documents with the highest cosine similarity to queryEmb, ordered from most similar to least similar. If k > N, return all document indices sorted by similarity. Function Signature def topKSimilar(queryEmb: np.ndarray, docEmbs: np.ndarray, k: int) -> np.ndarray
Viewing 261 - 270 interview questions