Machine Learning / AI
Do you have experience with time series and PySpark?
WildberriesWhat is LangGraph? Why use it instead of LangChain or raw API?
What to do when a block has a different amount of content — some have single blocks, and others have blocks with 30 items? How to work with content scores to get a feature from this block?
iviWhat IDE or shell do you use for working with AI tools?
Let's brainstorm how to repackage RAG experience for recommendation systems, and then typical questions. Just briefly, not how to answer, but the essence based on my experience and resume.
iviDo you plan to stay in the Philippines or move to another country?
Tell me about a regression project for predicting the market value of real estate and the model used.
НорникельDo you have offers in hand or final stages with other companies?
What is the complexity of the ROC-AUC algorithm?
iviWhat was the product at [company] from the user's perspective (document flow, data extraction from KS-2/KS-3/estimate)?
What was the object of the state (TypedDict or other)?
Why does structured output always produce valid JSON? At what level is this implemented?
How did these four agents write to the shared state so as not to overwrite each other's state?
How will you search for a table with data about a client, the company's director, and his field if you don't know where this data is stored and there's no one to ask?
Explain simply how your system works for a single user without asynchronous processes.
Is it always good when the scroll depth is large?.
iviIf one of the agents made a mistake, did the entire graph fail or reach the summary agent for degradation?
You have been working there for four years. Why are you planning to leave? Why are you considering an offer now?
What assumptions are needed to build a linear regression?
НорникельDescribe step-by-step the path of a user message through an LLM during inference — from chat to response, including architectural details of Transformer.