GenAI and LLM interview questions

An LLM is a neural net trained on huge text to predict the next token.

It is writing clear instructions, context, and examples so the model does the task you want.

RAG searches your documents first, then feeds relevant chunks into the LLM prompt.

Embeddings are numeric vectors that place similar meanings near each other.

I ground with RAG, constrain output schemas, add citation checks, and keep humans in the loop for high risk.

Balance context completeness versus retrieval precision.

Models accept a maximum context window measured in tokens, not words.

Max steps, budgets, and stop conditions.

Temperature controls randomness.

Measuring angle between vectors — common for nearest neighbor search.

An agent plans steps, calls tools like search or APIs, and loops until a goal is met.

Red-team prompt suites, automated classifiers, and human review.

A piece of text the model reads — often a word piece.

The instruction and context you send the model.

Randomness in token sampling.

Models and vector search work better on focused passages.

Ground the model on retrieved text, cite sources, and refuse when context is weak.

Untrusted content tries to override system instructions.

Golden sets, rubric scoring, latency, cost, and regression gates in CI.

Cache frequent prompts, trim context, pick smaller models for easy tasks, and set budgets with alerts.