How do you compare the quality of different embedding models? What is MTEB?
Machine Learning / AI
What is torch.compile and what are its limitations?
Gradient Descent, SGD, and Mini-Batch SGD: what are the differences, advantages, and disadvantages of each?
What data types are suitable as dictionary keys in Python and why?
Where did the area of responsibility end, and was there experience in writing production code?
How does boosting work and how is a boosting model built?
What is bagging and why does it reduce the variance of a model?
Why was CatBoost used?
What is doubly robust estimation?.
How are random forest and gradient boosting similar and different? How are trees built in each?
What normalization methods for data distribution exist?
What methods can be used to improve a model?
What is the difference between QAT and PTQ?
What is p-tuning?
What binary classification metrics do you know? The pros and cons of each.
What tools do you use for drawing diagrams?
What hypotheses exist in hypothesis testing?
What is a DAG in Airflow?