Top 19
Prep plan
Updated weekly · Last refresh Aug 30

American Express Agentic AI Engineer Interview Questions

The questions to prepare for a American Express Agentic AI Engineer interview. Questions from real interview reports rank first. Updated weekly.

19questions
~3htotal time
Track your progressSign up free to work through all 19 questions and resume where you left off.
Start practicing free →
1
Generative AI & LLMsStart here. 6 questions · ~49 min
Reduce Hallucinations in AnswersMedium

Design a grounded LLM assistant that cuts unsupported claims below 2% while meeting strict latency, cost, and safety limits.

HallucinationRAGLLM EvaluationAmerican Express
Integrate an LLM Agent SafelyMedium

Discuss integrating an LLM agent into an existing workflow, including evaluation, safety risks, system constraints, and business outcomes.

HallucinationRAGLLM EvaluationAmerican Express
More Generative AI & LLMs questions with a free account
2
System Design4 questions · ~32 min
Design an OAuth Integration Intelligence SystemMedium

Design an ML system that uses OAuth, SDK, and API integration signals to predict setup issues and improve developer integration success.

InfrastructureFeature StoreModel ServingAmerican Express
Design a Highly Available ML Serving PlatformMedium

Design a distributed ML serving platform that stays available and scales under failures, traffic spikes, and model updates.

distributed systemsscalabilityhigh availabilityAmerican Express
More System Design questions with a free account
3
Behavioral & Leadership5 questions · ~41 min
More Behavioral & Leadership questions with a free account
4
More topics4 questions · ~32 min
Diagnose AI Feature Engagement DropMedium

Approach for evaluating a drop in engagement metrics for an AI driven feature and separating model issues from product or traffic changes.

AccuracyThreshold TuningRecallAmerican Express
Data Governance in AI PipelinesMedium

Approach for governing data across AI pipelines, from ingestion and transformation to access control, quality checks, and auditability.

InfrastructureData ModelingQualityAmerican Express
Predict Customer BehaviorMedium

Train a supervised model to predict customer behavior from historical activity, profile, and interaction data.

Cross-ValidationFeature EngineeringSupervised LearningAmerican Express
Optimize Customer Data RetrievalMedium

Tests query optimization and performance thinking for large-scale customer data retrieval.

Hash TablesArraysSearchingAmerican Express

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 19 questions to finish this plan.