Backpropagation, RAG, Generative AI use cases, Given an initial state of loss function, alpha and x value, calculate the change in weight x if the algorithm is backpropagation.
Learning Engineer Interview Questions
6,588 learning engineer interview questions shared by candidates
- An assembly question about a SIMD architecture that I cannot remember exactly. - Given an array of points (x and y coordinates), implement a data structure (a heap) for insertion and deletion of n nearest ones. - Implement a CUDA kernel that computes the frequencies of numbers given in an array - Given a very large file containing integers, implement an algorithm that outputs sorted version. (also do space and time complexity analysis) - Implement an optimized CUDA kernel for matrix transpose (also had discussions about GPU architecture) - Present a system you designed and implemented, and explain the changes for desired features asked on the conversation. - Various questions about deep learning like explanation of optimization algorithms, difference between gradient descent and stochastic gradient descent, underfitting, overfitting, gradient clipping and many more.
Why do you want to join Virta?
They ask you about any project challenges you've overcome in your given field.
This was an interview screening, so it was introductory. The rudest introduction I have ever experienced in my 30 year career!
Niche role, asked relevant experience questions, went into detail on Patents and Research Papers
Talk about a challenging project.
Given historical stock prices, determine best date to buy and sell
Questions based on Resume, ML, Multi-threading, parallel programming, and C++
- Resnet, underfitting , overfitting, RELU, vanishing gradient. conv2d Leetcode 131
Viewing 6221 - 6230 interview questions