Top 25
Prep plan
Updated weekly · Last refresh Aug 30

CGI GenAI Engineer Interview Questions

The questions to prepare for a CGI GenAI Engineer interview. Questions from real interview reports rank first. Updated weekly.

25questions
~3htotal time
Track your progressSign up free to work through all 25 questions and resume where you left off.
Start practicing free →
1
Generative AI & LLMsStart here. 7 questions · ~57 min
Approach LLM Fine-Tuning for TasksMedium

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

Prompt EngineeringLLM EvaluationFine-TuningCGI
Fix Hallucinations in RAG AnswersEasy

Reduce hallucinations in a RAG system even when retrieval is already correct, using grounding, verification, and evaluation.

CGI
More Generative AI & LLMs questions with a free account
2
Machine Learning4 questions · ~33 min
Supervised vs Unsupervised LearningEasy

Explain how supervised and unsupervised learning differ, and ground the distinction in a practical ML example.

Unsupervised LearningFeature EngineeringBias-Variance TradeoffCGI
More Machine Learning questions with a free account
3
Model Evaluation3 questions · ~24 min
Improve Model AccuracyMedium

Approach for improving a model's accuracy by checking errors, features, and tuning choices.

Hyperparameter TuningCross-ValidationAccuracyCGI
More Model Evaluation questions with a free account
4
Coding3 questions · ~24 min
Preprocess Missing Values FunctionEasy

Tests practical coding skills for data cleaning and handling missing data correctly.

Hash TablesArraysMatrixCGI
More Coding questions with a free account
5
Behavioral & Leadership4 questions · ~33 min
More Behavioral & Leadership questions with a free account
6
More topics4 questions · ~33 min
Fine-Tune a Large Language ModelEasy

Explain a practical approach to fine-tuning an LLM, from tokenization and data prep to training and evaluation.

Hyperparameter TuningLanguage ModelsDeep LearningCGI
Design a Low Latency RAG PlatformHard

Design a low latency RAG system over millions of documents, with scalable retrieval, ranking, generation, and production monitoring.

low latencyscalabilityRAG architectureCGI
End-to-End ML PipelineHard

Tests your ability to design production-ready ML pipelines across data, training, and deployment.

ETLBatch ProcessingOrchestrationCGI
More 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
The finish line: interview-readyComplete all 25 questions to finish this plan.