Why did you choose a technical field with a humanitarian education?
Machine Learning / AI
What is bootstrap?
How does the support process occur: through git or manually?
What are contextual bandits and where are they applied?
How to simplify ResNet50 in a classification task?
How does TF-IDF differ from frequency representation and why is it needed?
How was the process of deploying the model to production? Did you prepare documents and artifacts for MLOps, have access to production stands, and could you run pipelines independently?
If we had unlimited resources and speed of convergence didn't matter, which method of GD, SGD, or Mini-Batch SGD would be better to use?
How do you approach solving an SQL problem?
What is test-time augmentation (TTA)?
What is target encoding for categorical features over time and how to avoid leakage?
What is a garbage collector and how does it work in Python?
Why and when to use graphics cards?
How to calculate the perplexity of a language model? What are its properties?
What is mediation analysis?
On an imbalanced dataset, the model has recall 100% and precision 1%. What happened?
What is LLaVA and how is it structured?
Tell me about hybrid retrieval in RAG — which model did you choose for dense vectors?
Why can model weights become large and why is it necessary to reduce them with regularization?
What is redaction and tokenization of PII in datasets?