Citi Machine Learning Engineer Interview Questions
The questions to prepare for a Citi Machine Learning Engineer interview. Questions from real interview reports rank first. Updated daily.
Design lag, rolling, and calendar features for a forecasting problem with temporal dependence.
CitiExplain how to train and evaluate models on highly imbalanced fraud data without relying on misleading accuracy.
CitiDesign a monitoring and maintenance process for detecting drift, measuring delayed-label performance, and safely retraining a deployed model.
CitiDesign a production and governance plan for deploying large neural networks while meeting regulatory, reliability, privacy, and auditability requirements.
CitiDesign a shared feature store for training and low-latency inference across many ML systems with strict freshness and consistency needs.
CitiDesign a real-time recommendation engine for Citi retail banking clients, including retrieval, ranking, serving, evaluation, and monitoring.
CitiExplain architectural patterns for reliable, low-latency ML inference in trading systems.
CitiSign up to see every question
Create a free account to unlock this list and practice real interview questions.
Tests ownership during an ML production failure, including diagnosis, cross-functional communication, and learning from offline-vs-production gaps.
Citi