Dataford
Top 20
Prep plan
Updated weekly · Last refresh Aug 30

Amazon Advertising Applied Scientist Interview Questions

The questions to prepare for a Amazon Advertising Applied Scientist interview. Questions from real interview reports rank first. Updated weekly.

20questions
~3htotal time
Track your progressSign up free to work through all 20 questions and resume where you left off.
Start practicing free →
1
CodingStart here. 3 questions · ~27 min
Efficient Chamfer DistanceHard
Practice

Compute symmetric Chamfer distance between vector sets using exact KD-tree nearest-neighbor search.

MathData StructuresAlgorithmsAmazon Advertising
More Coding questions with a free account
2
Machine Learning3 questions · ~27 min
Vanishing Gradients in Deep NetworksMedium

Explain vanishing gradients in deep networks and how residual connections, batch normalization, and activation choice improve training.

Neural NetworksDeep LearningGradient DescentAmazon Advertising
More Machine Learning questions with a free account
3
System Design3 questions · ~27 min
Multimodal Translation ML PipelineHard

Tests ability to design a full ML pipeline for multimodal translation, including data flow and model evaluation.

Feature StoreRetrievalModel ServingAmazon Advertising
Real-Time Ad Recommendation ArchitectureHard

Tests system design skills for low-latency, high-throughput ad serving with reliable ranking and retrieval.

Cold StartModel ServingRecommendation SystemsAmazon Advertising
More System Design questions with a free account
4
NLP3 questions · ~27 min
Perplexity for Language ModelsMedium

Tests understanding of core language-model evaluation concepts and their math.

Language ModelsEvaluation TechniquesAmazon Advertising
More NLP questions with a free account
5
Behavioral & Leadership5 questions · ~44 min
More Behavioral & Leadership questions with a free account
6
More topics3 questions · ~27 min
Explain Core Classification MetricsEasy

Explain precision, recall, F1-score, and ROC-AUC for a classification model.

F1 ScorePrecisionAUC-ROCAmazon Advertising
Seasonal Experiment FrameworkHard

Tests experimental design and statistical rigor for model validation under seasonality.

experiment designTime SeriesA/B TestingAmazon Advertising
Metrics for Noisy Crowdsourced DataHard

Tests ability to define robust dataset quality metrics under noise and reliability constraints.

Data QualityEvaluation TechniquesModel MetricsAmazon Advertising

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 20 questions to finish this plan.