Sobes.tech

Machine Learning / AI

Classification task with strong class imbalance: which metrics are good, which are bad?

Middle
160

What metrics did you use to evaluate system quality and how did you achieve a 40% improvement?

Middle+
160

What is the difference between the apply and map methods in Pandas?

Middle
160

Is a list a mutable data type in Python?

Middle
160

Pre-Layer Norm vs Post-Layer Norm — what is the difference and why is it important for training stability?

Senior
160

Where and what needs to be stored to ensure fault tolerance in auto-call rejection tasks?

Middle
160

How to extract text from scans?

Middle
160

Tell us about Batch Normalization: what it is and why it is needed?

Middle+
160

How can you achieve a strictly structured response model, for example in JSON?

160

What metrics were used to measure retrievability (which dataset and tool)?

Middle+
160

Rate your English separately for reading/writing and speaking according to CEFR levels.

Senior
160

How to train a model? Seq-to-seq is expensive, and there are many hyperparameters. How to do it?

Senior
160

Write a short paragraph for self-presentation, highlighting that recommendation systems are very similar to RAG - retrieval, reranking, architectural similarities, and so on, so I can remember and explain.

Senior
160

How do you consider the situation when a funny answer has many likes but is not correct?

160

Is the total experience of 3 years 2 months documented?

Middle
160

Did I understand correctly: we have a ranker with an average score from the content ranker based on content filling, with user and block features, and we took positive — what exactly?

Senior
160
/182