Notion
Software Engineer, AI Workflows
About this role
Notion seeks an AI Product Engineer to design and scale intelligent custom agents that automate workflows using LLMs and embeddings. You'll collaborate across teams to prototype, productionize, and enhance AI-powered features within Notion's core platform.
What you'll do
- Prototype and experiment with new AI features for custom agents
- Productionize and scale asynchronous workflows across Notion's systems
- Collaborate with AI, Infrastructure, and Product teams to deliver quality user experiences
- Stay current with latest AI technologies and trends
- Build AI products from ground up, spanning UI to data models
What they're looking for
- Building AI products with LLMs and embeddings
- Relational databases (Postgres, MySQL)
- Holistic problem-solving and critical thinking
- Clear communication and cross-functional collaboration
- React, TypeScript, Node.js (nice to have)
- End-to-end feature ownership
- User-focused impact orientation
- Navigating ambiguity and decomposing complex problems
Benefits
- Work on cutting-edge AI technologies at scale
- Collaborate with world-class AI, product, and infrastructure teams
- In-person collaboration culture with Anchor Days (Mon, Tue, Thu)
- Opportunity to shape the future of AI-powered work
- Learning and development investment in personal and team growth
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Notion
Notion builds an AI-powered collaborative workspace platform used by millions for productivity, featuring capabilities like search, automations, and AI-assisted features. The company is hiring software engineers for core product and AI development, technical support engineers for enterprise customers, data platform engineers for foundational systems, and security engineers for infrastructure and AI safety initiatives.
- Website
- notion.so
Likely interview questions
- Walk us through a time you built and shipped an AI-powered feature end-to-end. What was the most challenging part of moving from prototype to production?
- How would you approach designing a system to reliably handle asynchronous AI workflows at scale, and what are the key reliability challenges you'd anticipate?