Software Engineer, AI Platform

Notion Notion · Enterprise · San Francisco, CA · Engineering

Software Engineer, AI Platform at Notion, responsible for building and scaling shared foundations for AI products, ensuring their safety, reliability, and efficiency at scale. The role involves operating critical AI systems in production, enabling product teams to ship AI features faster, and managing quality/reliability gates.

What you'd actually do

  1. You'll own and play a pivotal role in the prototyping, development and scaling of systems and core AI platform primitives.
  2. You’ll partner closely with product teams to provide paved paths and production-ready guardrails that help new AI features ship faster with less duplicated work.
  3. You’ll work across infrastructure, shared libraries, APIs, and product integration points to make AI platform capabilities easy to adopt and high-leverage across Notion.
  4. You’ll operate critical AI systems in production, using observability and diagnostics to understand provider/model behavior, debug failures, improve latency and cost, and evolve systems with minimal user disruption.
  5. You’ll help Notion safely adopt new models, providers, and AI capabilities through versioning, controlled rollouts, compatibility layers, and clear quality/reliability gates.

Skills

Required

  • Experience with LLM, ML platform, data, or infrastructure teams that own critical shared systems
  • Understanding of challenges in scaling reliability, latency, cost, and quality
  • Ability to build dependable, efficient, and easy-to-use platforms
  • Ability to go deep on system behavior, especially with changing models, providers, and requirements
  • Ability to work across backend, infrastructure, libraries, and product code
  • Comfort working across ambiguous problem spaces
  • Ability to align stakeholders around a clear path forward
  • Ability to drive execution with accountability
  • Ownership of platform outcomes including reliability, quality, adoption, and operational follow-through
  • Ability to decompose ambiguous system behavior
  • Ability to debug across layers
  • Ability to work toward clean, pragmatic solutions
  • Pragmatic and business-oriented approach
  • Prioritization based on product and business impact
  • Balancing craft with urgency and operational simplicity

Nice to have

  • 2-4 years of experience as a Software Engineer
  • Experience with applied AI product development (prompting, evals, model integrations, or quality measurement)
  • Experience building out and scaling data processing pipelines at scale with Apache Spark or Ray
  • Past experience working full-stack in Typscript and node.js ecosystem
  • Experience building MLOps and ML serving infrastructure

What the JD emphasized

  • Passion for AI systems at scale
  • Extreme ownership
  • operate critical AI systems in production
  • quality and correctness systems like evals and release gates

Other signals

  • building shared foundations for AI products
  • operating critical AI systems in production
  • enabling product teams to ship AI features faster
  • ensuring safety and reliability of AI systems at scale