Machine Learning Engineer · Onsite · Multiple Types

[ OK ] c82eff47-504c-4ffb-9a62-516e2f10280c — full writeup

[ INFO ] category: Behavioral · Multiple Types difficulty: 6 freq: first seen: 2026-04-11

[6][MULTIPLE TYPES]Machine LearningSystem DesignAlgorithms

$ cat problem.md

Meta — Machine Learning Engineer ✅ Passed

Level: Senior-Level

Round: Onsite · Type: Multiple Types · Difficulty: 6/10 · Duration: 60 min · Interviewer: Neutral

Topics: Machine Learning, System Design, Algorithms

Location: San Francisco Bay Area

Interview date: 2025-08-15

This was my onsite interview. I was asked algorithm questions and a machine learning design question.

I had an onsite interview for a Machine Learning Engineer position.

Phone Screen:

Onsite:

Sliding window anagram
Data stream mean
ML design: Design a model to predict the probability of dislike of a Facebook newsfeed post. The interviewer didn't follow up much, and I went through the standard process with few interruptions.
We have a ML model that predicts the probability of like of a post in the Facebook newsfeed. How to leverage a new feature "post liked in the last 6 months"?
- Follow up: What if offline metrics don’t translate into online metrics?

LeetCode similar: LeetCode 528

user@intervues:~/experiences/meta$