Software Engineer, AI Platform - Notion

Who We Are

Notion is the collaborative AI workspace where teams and agents think together. We're building one place where your knowledge, projects, meetings, and AI tools live side by side. Our goal is to set the standard for how humans work together in the AI era.

About the Role

The AI Platform team is responsible for building the shared foundations that let Notion ship AI products quickly and operate them safely at scale. You will join a team focused on making speed and quality compatible, building reliability, observability, and shared primitives for model integrations, context management, and cost/performance tradeoffs.

Note: This role is based in San Francisco or New York City with a hybrid schedule (Anchor Days: Monday, Tuesday, Thursday).

What You'll Achieve

• System Ownership: Prototype, develop, and scale core AI platform primitives.
• Enablement: Partner with product teams to provide paved paths and production-ready guardrails.
• Cross-Functional Impact: Work across infrastructure, shared libraries, APIs, and product integration points.
• Operational Excellence: Operate critical AI systems in production, using observability to debug failures and optimize latency/cost.
• Safe Adoption: Facilitate the adoption of new models and providers through versioning, controlled rollouts, and quality gates.

Skills You'll Need

• Passion for AI Systems: Experience on LLM, ML platform, or infrastructure teams. Understanding of scaling reliability, latency, and quality.
• Adaptability: Ability to move across backend, infrastructure, and product code as requirements evolve.
• Extreme Ownership: Comfortable driving ambiguous problem spaces to clear outcomes.
• Problem-Solving: Ability to decompose complex system behavior and debug across layers.
• Pragmatism: Strong business orientation with the ability to balance craft, cost, and speed.

Nice to Haves

• 2-4 years of experience as a Software Engineer.
• Experience with applied AI product development (prompting, evals, model integrations).
• Experience scaling data processing pipelines (Apache Spark or Ray).
• Full-stack experience in the TypeScript and Node.js ecosystem.
• Experience building MLOps and ML serving infrastructure.