Top 11
Prep plan
Updated weekly · Last refresh Oct 17

Citi Agentic AI Engineer Interview Questions

The questions to prepare for a Citi Agentic AI Engineer interview. Questions from real interview reports rank first. Updated daily.

11questions
~1htotal time
Track your progressSign up free to work through all 11 questions and resume where you left off.
Start practicing free →
1
System DesignStart here. 5 questions · ~40 min
Single Model vs Multi-Agent TradeoffsHard
Recently asked

Compare single large-model and multi-agent architectures for reliable, scalable complex business logic.

agent workflowsmodel architecturemonolithic vs swarmCiti
Autonomous Ledger Update AgentHard
Recently asked

Design an agent that extracts, validates, authorizes, and safely applies ledger updates from unstructured email.

agent workflowsbackend integrationagent designCiti
Agent Memory and Context PersistenceHard
Recently asked

Design memory and context persistence for a long-running agent handling multi-step tasks.

agent workflowsagentic systemsagent designCiti
Human-in-the-Loop for High StakesHard
Recently asked

Design a Citi agentic workflow that routes high-stakes transactions through auditable human verification.

agent workflowsauthorizationfailure modesCiti
More System Design questions with a free account
2
Behavioral & Leadership3 questions · ~24 min
Mentoring a Junior AI EngineerEasy
Recently asked

Tests mentorship through a real delivery context, focusing on coaching style, feedback, communication, and measurable impact on both engineer and team.

MentorshipLeadershipOwnershipCiti
More Behavioral & Leadership questions with a free account
3
More topics3 questions · ~24 min
Privacy and Security for API InterfacesHard
Recently asked

Design a secure pipeline that lets an agent access internal APIs while enforcing identity, least privilege, privacy, auditing, and safe data handling.

APIsGovernanceapi accessCiti
Reliability and Hallucination EvaluationHard
Recently asked

Design an evaluation harness to measure autonomous-agent task success, hallucination rate, calibration, and robustness before production deployment.

experimental designmodel validationModel EvaluationCiti
Fail-Safe Handling for Agent FailuresHard
Recently asked

Tests how to detect autonomous-system failures, transition safely, contain side effects, and validate recovery mechanisms.

networking basicsfailure managementtechnical fundamentalsCiti

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 11 questions to finish this plan.