Software Engineer, AI Platform

Jobtailor; California (MO); On-site; USD 120,000 - 180,000; Full time

Job summary

Notion is seeking an engineer to own the prototyping, development and scaling of AI platform primitives. You will collaborate with product teams to provide production-ready guardrails that help new AI features ship faster with less duplicated work.

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.

Qualifications

• Experience with AI systems at scale and shared platforms.
• Experience on AI product development including prompting, evals, model integrations, or quality measurement.
• Built and scaled data pipelines (Spark or Ray).
• Full-stack experience in TypeScript and Node.js ecosystem.
• Experience building MLOps and ML serving infrastructure.

Responsibilities

• Own prototyping, development and scaling of AI platform primitives.
• Partner with product teams to provide production-ready guardrails for faster feature shipping.
• Work across infrastructure, libraries, APIs, and product integration points to enable easy adoption of AI capabilities.
• Operate critical AI systems in production, using observability to understand behavior, diagnose issues, and optimize latency and cost.
• Help Notion safely adopt new models and providers through versioning and controlled rollouts.

Skills

AI systems

LLMs

ML platform

Data pipelines

Full-stack TypeScript/Node.js

MLOps

Observability

Tools

Apache Spark

Ray

TypeScript

Node.js

Job description

Responsibilities

• You’ll own and play a pivotal role in the prototyping, development and scaling of systems and core AI platform primitives.
• 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.
• 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.
• 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.
• You’ll help Notion safely adopt new models, providers, and AI capabilities through versioning, controlled rollouts, compatibility layers, and clear quality/reliability gates.

Requirements

• Passion for AI systems at scale: You’ve worked on LLM, ML platform, data, or infrastructure teams that own critical shared systems. You understand the challenges of scaling reliability, latency, cost, and quality as usage and model complexity grow. You care deeply about building platforms that are dependable, efficient, and easy for other engineers to use.
• Adaptable and curious: You like going deep on how systems behave in practice, especially when models, providers, and product requirements are changing quickly. You’re eager to use AI tools to work smarter and are willing to move across backend, infrastructure, libraries, and product code when that’s what the problem requires.
• Extreme ownership: You’re comfortable working across ambiguous problem spaces, aligning stakeholders around a clear path forward, and driving execution with accountability. You take ownership of platform outcomes including reliability, quality, adoption, and operational follow‑through beyond team boundaries.
• Thoughtful problem-solving: For you, problem-solving starts with a clear and accurate understanding of the context. You can decompose ambiguous system behavior, debug across layers, and work toward clean, pragmatic solutions by yourself or with teammates. You’re comfortable asking for help when you get stuck.
• Pragmatic and business‑oriented: You understand that AI platform work is full of tradeoffs across quality, latency, cost, reliability, and speed of execution. You prioritize based on product and business impact, balancing craft with urgency and operational simplicity.
• 2-4 years of experience as a Software Engineer.
• Experience with applied AI product development (prompting, evals, model integrations, or quality measurement).
• You’ve built out and scaled data processing pipelines at scale with Apache Spark or Ray.
• You’ve past experience working full‑stack in Typscript and node.js ecosystem.
• You have experience building MLOps and ML serving infrastructure.

Core Competencies

Demonstrates expertise in AI systems at scale, with a strong focus on building dependable and efficient platforms. Proficient in full‑stack development, MLOps, and data processing pipelines, while effectively balancing quality, latency, and cost in AI product development.