Machine Learning Engineer · Phone Screen · Coding

Lyft — Machine Learning Engineer ❌ Failed

Level: Senior-Level

Round: Phone Screen · Type: Coding · Difficulty: 6/10 · Duration: 60 min · Interviewer: Unfriendly

Topics: Cross-Validation, Machine Learning, Model Deployment, Stratified K-Fold Splitting

Location: San Francisco Bay Area

Interview date: 2024-12-31

Got offer: False

Summary

This was a technical phone screen. The interviewer immediately had me introduce myself and then started the coding questions.

Details

The interview consisted of two parts:

Part 1: I was given a table of 5 cross-validation test errors:

` iterates test error

1 3.55 2 4.22 3 3.12 4 4.01 5 3.74 `

Based on this, I was asked what the performance of the model would be if deployed to a production environment. I was also asked how the model would be affected if a new feature, max(row values), were added, and similarly for min(row values).

Part 2: I was asked to handwrite a stratified k-fold splitting function. I remember the input and output, but I couldn't write it out completely.