Top 40
Prep plan
Updated weekly · Last refresh Oct 17

Coupang Machine Learning Engineer Interview Questions

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

40questions
~6htotal time
Track your progressSign up free to work through all 40 questions and resume where you left off.
Start practicing free →
1
CodingStart here. 8 questions · ~72 min
Two Sum CodingEasy
Practice

Find two Coupang item scores that sum to a target using a hash map in O(n) time.

Hash TablesArraysTwo PointersCoupang
Hard Dynamic ProgrammingHard

Tests problem-solving skill and ability to derive and implement DP solutions under difficulty.

RecursionDynamic ProgrammingArraysCoupang
More Coding questions with a free account
2
System Design9 questions · ~81 min
Design a Low Latency Inference PlatformHard

Design a low latency ML inference platform for high-frequency online predictions with strict response times and evolving model features.

high-frequency requestslatencysystem architectureCoupang
Design an Advertisement SystemHard

Evaluates system design thinking for an ads platform, including data, modeling, and serving.

Coupang
More System Design questions with a free account
3
Machine Learning8 questions · ~72 min
Supervised vs Unsupervised LearningEasy

Explain how supervised and unsupervised learning differ, and ground the distinction in a practical ML example.

Unsupervised LearningFeature EngineeringBias-Variance TradeoffCoupang
More Machine Learning questions with a free account
4
Behavioral & Leadership10 questions · ~90 min
More Behavioral & Leadership questions with a free account
5
More topics5 questions · ~45 min
Designing a Personalization ExperimentEasy

Design a basic A/B test for a recommendation idea, including metric choice, sample sizing, and how to interpret the result.

Confidence IntervalsExperimentationA/B TestingCoupang
Evaluate Precision and Recall TradeoffsMedium

Assess precision and recall for a model and explain how the threshold changes the tradeoff.

F1 ScorePrecisionRecallCoupang
ML Pipeline for High-Value CustomersHard

Assesses ability to design an end-to-end ML pipeline for customer value modeling at scale.

Coupang
More 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
The finish line: interview-readyComplete all 40 questions to finish this plan.