Top 38
Prep plan
Updated weekly · Last refresh Oct 17

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 daily.

38questions
~6htotal time
Track your progressSign up free to work through all 38 questions and resume where you left off.
Start practicing free →
1
CodingStart here. 3 questions · ~28 min
Fix Failing Python TestsHard
Practice

Diagnose failing class methods, correct state updates, and aggregate wallet balances by tier.

CodingData Structuresedge casesAmerican Express
Deadlock Detection in Agent GraphsHard
Practice
Recently asked

Use Tarjan's algorithm to identify agents belonging to cyclic dependency components that may cause multi-agent deadlocks.

multi-agent systemsdfscycle detectionAmerican Express
More Coding questions with a free account
2
System Design12 questions · ~112 min
Design an Agent System for a Multi-System WorkflowHard

Design an agent that investigates, summarizes, and executes work across four to five independent systems.

agent workflowsbackend integrationagent designAmerican Express
Describe How Agents Gain CapabilitiesMedium

Explain how agents acquire, select, authorize, and safely execute capabilities through tools, APIs, and feedback loops.

agent workflowsagent designAPI interactionAmerican Express
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
Generative AI & LLMs11 questions · ~103 min
Autonomous Agent Workflow DesignHard
Recently asked

Design an evaluated, secure agent workflow using MCP tools and Agent-to-Agent delegation under latency, cost, and hallucination constraints.

agent workflowsPrompt Injectiontool useAmerican Express
More Generative AI & LLMs questions with a free account
4
Behavioral & Leadership9 questions · ~84 min
More Behavioral & Leadership questions with a free account
5
More topics3 questions · ~28 min
Diagnose AI Feature Engagement DropMedium
Recently asked

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
Predict Customer BehaviorMedium
Recently asked

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

Cross-ValidationFeature EngineeringSupervised LearningAmerican Express
Data Governance in AI PipelinesMedium
Recently asked

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

InfrastructureData ModelingQualityAmerican Express
The finish line: interview-readyComplete all 38 questions to finish this plan.