Top 23
Prep plan
Updated weekly · Last refresh Oct 17

Spotify Machine Learning Engineer Interview Questions

The questions to prepare for a Spotify Machine Learning Engineer interview. Questions from real interview reports rank first. Updated daily.

23questions
~3htotal time
Track your progressSign up free to work through all 23 questions and resume where you left off.
Start practicing free →
1
CodingStart here. 5 questions · ~45 min
Most Frequently Co-Played ArtistsMedium
Practice

Count unordered artist pairs appearing in Spotify streaming sessions and return every pair with the highest session count.

Hash Tablesaggregationfrequency countSpotify
Rolling 7-Day Active Users SQLMedium

Tests SQL windowing, aggregation, and translating product metrics into queries.

Window FunctionsaggregationsqlSpotify
Algorithm Under Time ConstraintsHard

Tests core coding ability and problem-solving under performance constraints.

RecursionparsingTreesSpotify
More Coding questions with a free account
2
System Design7 questions · ~62 min
Design a Cold Start RankerMedium

Design a recommendation and ranking system that handles cold start for both new users and new items without hurting feed quality.

Cold StartTwo-Tower ModelsRecommendation SystemsSpotify
Spotify Recommendation System DesignHard

Evaluates end-to-end system design for Spotify personalization, including data, ranking, and serving.

data pipelinedesignSpotify
More System Design questions with a free account

Sign up to see every question

Create a free account to unlock this list and practice real interview questions.

Get my prep plan
3
Behavioral & Leadership8 questions · ~71 min
More Behavioral & Leadership questions with a free account
4
More topics3 questions · ~27 min
Song Recommendation SystemMedium

Evaluates your approach to building and validating ML recommendation systems for Spotify-scale personalization.

Spotify
Real-Time Clickstream Data PipelineHard

Tests data engineering design for low-latency ingestion, correctness, and training readiness.

data integrationStream ProcessingETLSpotify
Optimizing Distributed Matrix FactorizationHard

Tests ML optimization skills for scalability, efficiency, and convergence in distributed settings.

distributed trainingsparkSpotify
The finish line: interview-readyComplete all 23 questions to finish this plan.