1:1 mentoring with Big Tech AI engineers
// interview prep

AI Engineer & FDE interview preparation

18 system design walkthroughs, 60 knowledge questions with model answers, 5 applied scenarios, and a strategy playbook for AI engineer and forward deployed engineer interview loops.

self-pacedreal interview questions
// how to prepare

A five-step preparation plan

  1. 01

    Learn the building blocks

    Get fluent in the agent loop, retrieval, and tool protocols before you practise answering questions about them.

  2. 02

    Drill the knowledge questions

    Say each answer out loud in under two minutes, then read the model answer and note what you missed.

  3. 03

    Practise system design

    Work a full design end to end: requirements, architecture, failure modes, evaluation, and cost. Then draw it in the Design Studio for an AI review.

  4. 04

    Work the applied scenarios

    Customer-style problems with a tradeoff at the centre, the kind FDE loops use to test judgement on a real deployment.

  5. 05

    Rehearse the loop

    Run through the playbook for how each round is scored and what interviewers listen for.

// sample answers

What a strong answer sounds like

What's the difference between a chatbot and an agent?

"A chatbot is a single LLM call — input in, text out, stateless. An agent is an LLM inside a loop. The loop gives it tools, memory, and the ability to take actions in the world. The agent decides what to do next based on observations. The key difference is autonomy — an agent can reason, act, observe, and iterate until…

Read the full answer →

When would you NOT use an agent? When is a simple RAG pipeline enough?

"If the task is single-turn retrieval + generation — user asks a question, you find the answer in docs — RAG is cheaper, faster, and more predictable. I'd reach for agents only when: (1) the task requires multiple steps (2) it needs tool use (write operations, calculations, API calls), or (3) the solution path is not k…

Read the full answer →
// practice tracks