Question Bank
Machine Learning interview questions
Naming a model or a metric is only the start of an interview answer. Explain why it fits the task, and connect training, regularization, validation and evaluation to a concrete example. Start with your own explanation, then state its assumptions and limitations.
Showing 20 of 746 questions
How is a recommendation system for real estate built?
What to do with severe class imbalance?
What metrics to use with class imbalance?
What exactly does the model output? Car brand, color, or other characteristics?
What architecture was chosen for the backbone - pre-trained network or training from scratch?
What domains involved participation in the full pipeline from data collection to inference?
Which project required continuous model retraining and what was it used for?
Was CI/CD already configured or did you have to modify it yourself?
Is there experience with inference optimization using TensorRT, quantization, and similar techniques?
Is it possible to solve the task in post-processing?
What are the pros and cons of this approach?
How to adapt first-person VR model for third-person video without additional labeling?
Who handles the other ML projects in the team?
Are services written in Python and backend developer helps with deployment and infrastructure?
How is the effect of machine learning models measured? Are A/B tests conducted on key metrics?
How to plan data processing without production infrastructure?
How to use user data and logs for machine learning?
How to ensure security of sensitive data when providing it?
What risks are associated with using personal data for model training?
Prepare for your next interview with Vibe Interview.
Download Vibe Interview