LLM
Also written as Large Language Model
A large AI model (like GPT or Claude) trained on huge amounts of text, able to understand and generate human-like language.
Think of it like
Like a widely-read scholar who's absorbed a huge slice of the world's writing and can now hold a fluent conversation about almost anything.
Junior or senior?
Junior sounds like
Has used ChatGPT and calls that LLM experience.
Senior sounds like
Has actually built with LLMs — prompting, fine-tuning, RAG, or the surrounding application.
Ask them
“What have you actually built with an LLM — prompting, fine-tuning, evaluation, or the surrounding application?”
Sounds like real experience
Names a specific application, prompt-design decision, or evaluation approach — and a real failure mode (hallucination, cost, latency) they had to design around.
Probe further if
Describes 'using an LLM' as calling an API without describing a specific design decision, evaluation, or failure mode they actually dealt with.