Interview Prep
AI & ML Fundamentals Interview Questions
Core concepts every AI interview opens with — AI vs ML vs GenAI, training vs inference, overfitting.
1
Beginner
What is the difference between AI, machine learning and generative AI?
AI is the broad goal of machines doing tasks that need intelligence. Machine learning is the approach of learning patterns from data instead of hand-written rules. Generative AI is the subset of ML whose models create new content — text, images, code.
Key Points:
- GenAI models are usually ML models trained on huge datasets.
- Not every AI system learns; rule-based systems are AI but not ML.
2
Intermediate
What is overfitting and how do you prevent it?
Overfitting is when a model memorises training data and fails on new data. Prevent it with more data, regularisation, simpler models, early stopping and a proper validation split.
Key Points:
- Watch the gap between training and validation scores.
- Cross-validation gives a more reliable estimate.
3
Beginner
What is the difference between training and inference?
Training adjusts a model's weights from data; inference uses the trained, frozen model to make predictions. Inference cost and latency matter most in production.
Key Points:
- Most LLM app work is inference, not training.