ML Mentor
Назад к подготовке
Constructor
Post-interview feedbackSeptember 25, 2025Constructor

Technical interview at Constructor

Constructor technical screen in English: background on HNSW/Qdrant vector search, a RandomizedSet coding task with insert/remove/getRandom in O(1), then a product/ML case for a URL and text summarization service covering input routing, chunking, web-page extraction, content cleaning, summarization evaluation and user feedback.

3 questions3 cases1 task1 hr 3 minAudio recording available
Question languageРусскийEnglishОригинал
Пройти собеседованиеВесь ход интервью

Аудио и материалы

Аудио скрининга

0:00 / 1:02:49

Этап 3 из 3ConstructorML Engineer, AI-агенты для покупок2025-08-28 - 2025-09-25
Собеседования в Constructor: ML Engineer, AI-агенты для покупок

Техническое собеседование в Constructor

Этап 2Весь процесс

Выводы и как готовиться

  • The coding task is the classic RandomizedSet: array for uniform random, hash map for indices, swap-with-last for O(1) deletion.
  • The ML case tests problem navigation more than backend architecture: URL/text routing, content extraction, LLM summarization paths and evaluation.
  • The vector-search prelude is useful production material because it asks how embeddings move from Airflow/Python into Qdrant HNSW and how indexes are refreshed.
Technical interview at Constructor — ML Mentor