All interviews
Notion logo

Notion

Mid

AI Product Engineer at Notion — building the LLM-powered Custom Agents that automate recurring team workflows

This role builds the AI-powered features behind Notion's Custom Agents, which automate recurring workflows like filing tasks, writing reports, and answering knowledge-base questions. It's framed as an 'AI Product Engineer' position emphasizing prototyping with LLMs and embeddings, productionizing async workflows at scale, and cross-functional collaboration with AI, Infrastructure, and Product teams. The JD does not specify a hard years-of-experience floor for the core bar, though the nice-to-haves reference 10+ years as a stretch signal, so this reads as a mid-level bar with room for a strong generalist.

Step into this interview

Free · a live voice mock calibrated to this exact role

Practice this interview

What this interview tests

  • Building AI product features using LLMs, embeddings, and other ML technologies
  • Productionizing and scaling asynchronous workflows
  • System design from UI through data model, with relational databases (Postgres/MySQL)
  • Decomposing ambiguous problems into clean, shippable solutions
  • Cross-functional collaboration with AI, Infrastructure, and Product teams
  • Communicating technical decisions clearly to varied audiences

Common question themes

Walk through an AI feature you built end-to-end using LLMs or embeddings, from prototype to production

How did you scale an asynchronous workflow that started as a quick prototype

Describe a time you had to decompose a genuinely ambiguous problem into a concrete plan

Tell me about a technical decision you had to explain clearly to a non-engineering stakeholder

How do you think about the real-world impact of an AI feature on users, good and bad

Describe a disagreement with a teammate about technical approach and how you resolved it

View the original posting

Related interviews