Easy

Interview

How do you keep up with AI when the field moves so fast?

Filter for 'do you actually engage with the field' vs 'studied for the interview last week'.

Interview

Why do you want to work in AI?

Tests motivation depth + ability to communicate authentically. Generic answers signal you'd be bored quickly.

Interview

Write code to evaluate a binary classifier and produce all the metrics that matter.

Tests whether you know what to actually measure beyond accuracy.

Interview

Look at this code snippet — what's wrong?

Tests whether you spot data-leakage bugs reflexively. They're the most expensive mistake in ML.

Interview

You're building a fraud detection model where 0.1% of transactions are fraud. Why is accuracy a bad metric and what should you use?

Tests practical evaluation knowledge — the imbalanced-class case is where most metric mistakes happen.

Interview

Your model has 95% training accuracy but 60% test accuracy. What do you investigate?

Classic diagnostic question. Tests whether you have a structured debugging process, not just memorized fixes.

Interview

What's the difference between L1 and L2 regularization, and when would you use each?

Quick check on fundamental ML knowledge — and whether you can connect math to practical model behavior.

Interview

How do you split data for a time-series model? Why not just random split?

Quick filter for whether you've worked with temporal data — this is the single most common ML mistake.