Interview Practice
Technical Screen
Explain, compare, and defend core AI engineering concepts.
What interviewers evaluate
- Precise definitions
- One concrete example
- Stated assumptions and known limits
- Adapting when a constraint changes
What you will be asked
Compare two approaches and say when you would pick each.
In the room
The interviewer names two options, such as long context and retrieval, a workflow and an agent, or a hosted API and a self-hosted model, and asks you to compare them for a stated product.
Timebox
30-45 minutes, 3-5 questions
Mock interview
A timed answer to a random question from this level, then the reference answer and your score.
How to practice
- Pick one linked comparison and write your answer before you open the study guide, then compare it with the reference answer.
- Use one table for both options: what each is good at, what it costs, and how it fails.
- With a peer: they change one constraint (latency, data freshness, or cost) and you say whether your choice changes.
What a strong answer shows
- States the product goal and constraints before comparing
- Compares both options on the same dimensions
- Names the evidence that would settle the choice, such as a small fixture set
- Says what would change the decision
Questions for this level
Each question opens on its Practice tab, and Previous and Next follow this list.
LLM Foundations
3 h
Compare sending whole documents in a large context window with retrieving a few passages for two features of one product, using window fit, cost with prefix caching, latency, access, and a sliced pilot, and say what would change each choice.
Tool Calling & Agents
3 h
Compare a fixed workflow and an agent loop for a parcel-delivery assistant's rescheduling and stuck-parcel tasks using a pilot's success, cost, and latency figures, then recommend a design per task and say what would change it.
Model Serving & Inference
3 h
Compare a hosted model API with a self-hosted open-weight model for a live tutor and a nightly scoring job: apply a quality gate, compute monthly cost at real utilization and the breakeven volume, check a data-location rule, and say what would reverse the choice.
Embeddings & Retrieval
3 h
Rank four help articles by shared words and by cosine similarity, score both rankings against labels, and explain a dense miss and an accidental lexical success.
Follow-up questions
An interviewer may ask these next.
- When does exact-match search beat embeddings?
- When is fine-tuning worth it over better prompts or retrieval?
- When would you use a fixed workflow instead of an agent loop?
- At what volume would you move from a hosted API to your own model, and what else would have to be true?
- How would you test which option is better on your own data?
Scoring rubric
Interview ready at 8 of 10 with no 0.
| Dimension | 0 | 1 | 2 |
|---|---|---|---|
| Problem framing | Jumps to a solution or solves the wrong problem | Restates the problem but misses key constraints or success criteria | Clarifies goals, constraints, and success criteria before solving |
| Correctness | Key claims or code are wrong | Mostly right with gaps or unhandled cases | Correct and precise, including edge cases |
| Evidence or testing | No way to verify the answer | Generic testing ideas | Concrete fixtures, metrics, or traces that would confirm or refute the approach |
| Trade-offs | One option, no alternatives | Names alternatives superficially | Compares options against the stated constraints and says what would change the decision |
| Communication | Disorganized or unclear | Understandable but meandering | Structured and concise; states assumptions; checks in with the interviewer |