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.

1635
questions
16
categories
50
companies

Showing 20 of 746 questions

MediumMachine Learning

How to use embeddings from images and descriptions?

#ml#ranking
Practice in bot
MediumMachine LearningConstructor

Do you use AI assistants and LLMs in your work?

#ml#ranking
Practice in bot
MediumMachine LearningInfomedia

What types of candidate generation exist in transformers?

#ml#transformers
Practice in bot
MediumMachine LearningCorsearch

Is Python used as the main development stack?

#ml#startup#data
Practice in bot
MediumMachine LearningCorsearch

Do ML engineers handle model deployment completely?

#ml#startup#data
Practice in bot
MediumMachine Learning

Understanding of task and infrastructure requirements

#ml#data_science#engineering
Practice in bot
MediumMachine LearningZinBrains

Explain bias-variance decomposition for decision trees and gradient boosting

#ml#data_science#engineering
Practice in bot
MediumMachine LearningZinBrains

How does IVF index work in FAISS?

#ml#data_science#engineering
Practice in bot
MediumMachine LearningZinBrains

How does implicit ALS (Alternating Least Squares) work?

#ml#data_science#engineering
Practice in bot
MediumMachine Learning

How does Unbiased Learning work for ranking (possibly CatBoost)?

#ml#data_science#engineering
Practice in bot
MediumMachine LearningZinBrains

Have you worked with NDCG metric? How is it calculated?

#ml#data_science#engineering
Practice in bot
MediumMachine LearningZinBrains

Have you worked on model deployment? What tools did you use?

#ml#moderation#recommendation
Practice in bot
MediumMachine LearningZinBrains

How do you approach selecting models for content generation?

#ml#moderation#recommendation
Practice in bot
MediumMachine LearningZinBrains

How to process requests for describing generated images?

#ml#moderation#recommendation
Practice in bot
MediumMachine LearningZinBrains

When comparing LLM with BERT, which model is better and why?

#ml#moderation#recommendation
Practice in bot
MediumMachine LearningАвито

Does the search system work across the entire Avito database or only within specific groups?

#ml#data#AI
Practice in bot
MediumMachine LearningАвито

What agent architecture is used for accessing internal company data?

#ml#data#AI
Practice in bot
MediumMachine LearningАвито

How did you determine the question domain for AI assistant and product strategy?

#ml#data#AI
Practice in bot
MediumMachine LearningАвито

How did you use filters with embedding-based search?

#ml#data#AI
Practice in bot
MediumMachine LearningАвито

How to work with embedding volume limitations?

#ml#data#AI
Practice in bot

Prepare for your next interview with Vibe Interview.

Download Vibe Interview
Machine Learning interview questions — page 36 | Vibe Interview