Notion
Software Engineer, AI Platform
About this role
Join Notion's AI Platform team to build foundational infrastructure that enables safe, scalable AI product development across the company. You'll own core AI systems, work with product teams to create reliable guardrails, and help Notion adopt new models and capabilities while maintaining quality and performance at scale.
What you'll do
- Prototype, develop, and scale AI platform primitives and core systems
- Partner with product teams to provide production-ready guardrails and paved paths for AI feature shipping
- Design and maintain infrastructure, shared libraries, and APIs for AI capabilities across Notion
- Operate critical AI systems in production with observability and diagnostics to optimize latency, cost, and reliability
- Enable safe adoption of new models, providers, and AI capabilities through versioning and controlled rollouts
- Debug cross-layer failures and drive system improvements with minimal user disruption
What they're looking for
- LLM/ML platform and infrastructure systems experience
- Scaling reliability, latency, cost, and quality in production systems
- Backend, infrastructure, and library development
- System observability and diagnostics
- Debugging complex distributed systems
- Problem decomposition and cross-functional alignment
- AI/ML concepts and model integration fundamentals
- Cost and performance optimization trade-off analysis
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
- Describe a time you owned a critical shared platform system—how did you ensure reliability and adoption?
- Tell us about your experience debugging model or LLM provider behavior in production. What tools did you use?