Extremely technical obscure questions related to what they in particular have recently read. Eg questions on “efficient” ways to reduce the dimensionality of a very large weight matrix. Answer isn’t even LORA rank decomposition it’s randomly removing rows and columns. Why can this work? Some obscure mathematics field I’d not heard of even with a masters in physics and PhD in ML. Very frustrating imo, but in fairness it does reflect what they were looking for.
An activity recognition problem for take home test. Follow up on code and design choices. In system design, questions on Kubernetes and video processing
Machine learning concepts: Unsupervised v/s supervised, overfitting, underfitting, performance metrics, choice of algorithm for any application
Git, statistics, ML multiple choice questions.
What is the significance of p-value?
Walk me through a CV project for detecting pedestrian
Difference between L1 and L2 Error
Tell me about yourself, and why this job
tell us a little bit about yourself
can do shift ot not
Viewing 1251 - 1260 interview questions