Банк вопросов из реальных собеседований

The catalog and photos are constantly changing. How to retrain the model and update the visual search ANN index?

After launching a feed recommender, how do you decide when and how to retrain the models?

How would you define requirements for a platform that trains large models on temporarily idle GPUs in multiple data centers?

Why does the attention mechanism itself not encode the order of tokens, and what absolute and relative positional schemes are used in language models?

Why does the attention mechanism itself not encode the order of tokens, and what absolute and relative positional schemes are used in language models?

A vector search returns top-k nearest items, but all results are too similar to each other. How can you keep relevance while increasing diversity?

A deployed LTV model works acceptably on average but badly for some apps. How would you find where and why it fails?

A video-analytics platform wants an assistant that answers support requests using documentation and prior tickets. How would you design the RAG system?

How to choose thresholds for phishing warnings and what metrics to monitor in production?

You need to design a ML system that personalizes the minimum order amount or shipping cost below the threshold. How to define the goal, the boundaries of the solution and the plan of the first version?

We need to make a block of recommendations in the basket for 10 million users and 100,000 products. How to determine the purpose, limitations and composition of the first version?

The company gave annual guidance for production growth. Why is it dangerous to spread it evenly across neighborhoods?

You need to do a search/hints in the database of articles or bank answers. Why is it wise to start with BM25/TF-IDF rather than straight away with embeddings/RAG?

What determines the high share of acceptance of preliminary tokens and why the average value should be analyzed by positions and types of requests?

It is necessary to estimate or suggest the price of the advertisement for the sale of used goods. What are the signs and basic options to offer?

Why can seller traits help a pricing or ranking model in a classifier and what equity and cold start risks need to be controlled?

How do you determine whether the new model will improve the product and justify the cost of switching from the current solution?

There is an idea to determine the audio event around the user: a dog barking, opening a door or broken glass. How to check product benefits before model training?

There is an idea to determine the audio event around the user: a dog barking, opening a door or broken glass. How to check product benefits before model training?

You need to predict retention, revenue or LTV over time. How to set a task, choose a horizon and granularity, build a baseline and carry out correct time validation?

After selecting price model features or recommendations, how to determine the target variable, partition, baseline, model and launch criterion?

Why is it necessary to disassemble the entire path of the user and the operational process of order execution before choosing a delivery model?

Intercommodity recommendations may not have neighbors: the product is new or rare, the user is new or the basket consists of many products. What backup scenarios are needed?

What are the operational features of the kitchen and couriers available to the delivery cost models and how to separate them from the stable user signs and the cooking point?