Банк вопросов из реальных собеседований

In international search, you need to show a short description of the object in the response card, for example for China. How to build a ML system for generating such descriptions?

Design a semantic search layer for geo/address suggestions where users can type categories like "cafe" and expect restaurants, POIs and relevant addresses across many languages.

What Unit Index, Update, Filters, and Evaluation Decisions Should Be Completed Before Adding a Re-Ranker?

How would you build a dataset that estimates a user’s response to a delivery fee or minimum order threshold?

How to independently code text and road segment, build a vector index and train a quick search for candidates?

How to design candidate generation and ranking for selecting suppliers for a procurement application in the corporate procurement marketplace?

There is a DSSM-like model trained in click-through sessions with the original, positive and negative merchandise. How to add text embedding products from LLM?

How do you apply perception, prediction and maps from an existing autonomous driving system to search for traffic scenes?

What should you do if delivery terms changed rarely in the past and there is almost no action variation from which to learn elasticity?

We need to add a LLM agent to the existing product pipeline. How to design agent boundaries, tools, context, checks and monitoring?

There is a domain search where generic embeddings do not work well. How to retrain the encoder and check that retrieval has become better?

There is an auto ad base and an anchor ad. You need to find archival ads where visually another car: a different color, interior, wheels, body or angle. How to set a task and train a model?

There is an LTV/retention forecast for cohorts. For old cohorts there are 7/30/180 days of history, and for new ones there is only an install or trial. How to make a forecast today?

In addition to answering the free-text question, you need to show related articles. How to form them: in advance or depending on the request, and where is the reranker needed?

The casino product data is stored in storage and comes through a message queue. You need to regularly update the signs and prompt users. How to design a production pipeline?

Есть реальный продуктовый use case: customer support automation. Нужно сравнить два LLM/agent variants и выбрать, какой запускать. Как спроектировать evaluation: данные, offline metrics, human/LLM judging, system metrics и online validation?

There is a transformer model of user history recommendations. How to make sure that it does not break the online service?

How would you enforce category compatibility and complementarity when candidates are retrieved from an ANN index over product embeddings?

There is a sequence of representations of the road scene beyond the time window, in which several rare events can occur simultaneously. How to set a task and build a basic solution?

After hybrid retrieval, you can give several articles to LLM. When is this justified, and when is it better to leave a regular reranker and a list of results?

What labels should we collect to teach how to select a test question and how to deal with the fact that we only see answers to the questions shown?

What features of existing models, maps, conditions and source quality should I add after vector search?

Which offline and online metrics would you use for a similar-items recommender, and what pitfalls are easy to miss?

Sketch the online architecture for query parsing, candidate generation, ranking and blending. How do services communicate and fail safely?