Are you only interested in RAG or in Data Science in general? Are you interested in anti-fraud direction?
Machine Learning / AI
How is a dictionary organized in Swift?
How to split documents into chunks? What size of chunks is usually chosen?
What is the time complexity of the solution in O notation?
What methods for combating overfitting exist and how do they work?
Do you know the key implementations of gradient boosting and their features?
How does AutoML for tabular data differ from CV/NLP?
What tools and libraries can be used when solving problems in Python?
How to organize anomaly detection based on model metrics?
Tell about the Adam optimizer: what does it consist of?
How to simplify the solution to traverse the list fewer times?
What depth of trees is used in Random Forest and boosting?
Tell us about Dropout: how does it work during training and what happens to it during inference?
If we do not use an explicit formula, how do we solve the linear regression problem?
What is the idea behind ensemble methods? What types of ensembles do you know?
What is SwiGLU and in which models is this activation used?
How will ROC AUC change when duplicating positive and negative objects and why?
What is the difference between gradient boosting and random forest?
What are stacking and blending?
How to form a metric that considers expected profit and the probability of sale by categories?