Interview prep · Q&A
Every question you'll actually get
Not a book, not 2,700 problems — the questions that come up in real AI-engineering loops, each with a short honest answer and why the interviewer is asking. Mark them as you go; state lives in this browser.
Asked at
6 of 6
| Question | Difficulty | Topics | Track | Marked |
|---|---|---|---|---|
| What is a token, and why does the same prompt cost different amounts on different models? | easy | tokensfoundationscost | foundations | |
| Design a chatbot that answers questions about our internal documentation. Walk me through the components and where the failure modes are. | hard | system-designragproduction | interviews | |
| How would you defend a customer-support agent against prompt injection when it can send emails and read a customer database? | hard | securityagentsproduction | production | |
| What's the difference between an eval and a benchmark, and why would a team run both? | medium | evalsproductionquality | production | |
| Temperature and top-p both control randomness. What's the difference, and when would you reach for each? | medium | samplingapisdecoding | apis | |
| Give me three cases where semantic search over embeddings retrieves the wrong document — and explain why. | medium | ragembeddingsretrieval | rag |