Arizona State University AI Engineer Interview Questions

Explain a practical approach to fine-tuning an LLM for a specific task, including data, evaluation, and hallucination risks.

Prompt EngineeringLLM EvaluationFine-TuningArizona State University

Approach for improving a production AI model using evaluation, threshold tuning, calibration, and targeted error analysis.

PrecisionAccuracyRecallArizona State University

Explain how to preprocess missing data for a supervised learning task without introducing leakage or degrading model quality.

Cross-ValidationFeature EngineeringSupervised LearningArizona State University

Explain a practical feature selection process using validation, regularization, and model-based importance to improve generalization.

Cross-ValidationFeature EngineeringRegularizationArizona State University

Design a cloud ML deployment system for a security product, covering training, serving, updates, and production monitoring.

InfrastructureFeature DriftModel ServingArizona State University

Approach for handling missing data in an ML data pipeline, including validation, imputation, and safe downstream consumption.

InfrastructureETLBatch ProcessingArizona State University