What distributions exist and where are they applied?
Machine Learning / AI
Design an auto-tagging system for products by photo on a marketplace.
What is a 1x1 convolution and what is it used for?
Why does a network with BatchNorm converge faster?
What is feature engineering for time series (lags, rolling stats, datetime features)?
Why did you leave your previous jobs and what is important to you in a new position?
Why can't accuracy be directly optimized?
What are the fundamental differences between GloVe and word2vec?
What LLM evaluation benchmarks do you know (MMLU, BBH, GSM8K, HumanEval)?
What methods are used for anomaly detection in images (PaDiM, PatchCore)?
What loss functions and metrics are best to use when forecasting demand for perishable goods?
Tell about quantization of models: what it is, why it is needed, and what types exist.
When did you join 1C-Rarus? Did you have a mentor or supervisor who helped you immerse in the tasks?
How is the RAG architecture organized?
When does deep learning outperform GBDT on tabular data?
How to organize human eval of LLM responses in a team?
What is self-supervised pretraining for GNN?
How to check the quality of new features and hypotheses in risk models and what metrics to use?
Design a relevance scoring system for search results with LLM-judge.