Назад к подготовке
Sber / GigaChat
Real technical interviewMarch 25, 2026

Interview at Sber / GigaChat

A real interview with the full timeline, linked technical questions and practice materials from Sber / GigaChat.

10 questions1 hr 7 minAudio recording available

Аудио и материалы

Аудио собеседования

0:00 / 1:06:54

Выводы и как готовиться

  • LLM theory interviews often move quickly across architecture, training and inference systems.
  • Good answers connect formulas to cost: sequence length, KV cache memory, attention complexity and distributed communication.
  • поиск embeddings should be evaluated with поиск metrics, not generic classification accuracy.
Interview at Sber / GigaChat — ML Mentor