Toloka AI
Фидбек после собеседованияФидбек после собеседования2025-09-30
Toloka AI: ML System Design
System design for checking human/agent task outputs with LLM tools and evaluation metrics.
Аудио и материалы
Аудио собеседования
0:00 / 53:38
Этап 4 из 4Toloka AIML / LLM Agent Engineer2025-09-11 - 2025-09-30
Собеседования в Toloka AI: ML / LLM Agent EngineerML System Design в Toloka AI
Выводы и как готовиться
- The core design is not only an LLM prompt: it needs a structured error taxonomy, evidence gathering and evaluation against human reviewer outputs.
- Metrics are set-valued and asymmetric: false accepts and false rejects have different operational costs.
- Manual-review budget is a hard product constraint, not an afterthought.