4 hours ago
Base Salary
$255k - $300k/yr
Responsibilities
- Integrate new frontier models into production for Notion users and engineering teams.
- Improve inference reliability through error categorization, self-healing retries, and cross-provider failover.
- Own observability for the model layer and reduce detection and remediation time.
- Build model-level capabilities and support product-team adoption.
- Coordinate across Notion’s AI teams to identify gaps, unblock work, and ensure fixes reach the appropriate owners.
- Define and use evaluations to measure prompt and model changes.
- Balance inference latency, cost, and output quality.
Requirements
- Hands-on experience building and operating production AI systems on top of LLM APIs.
- Understanding of token economics, streaming, tool calling, context limits, and production failure modes.
- Ability to evaluate model and prompt changes using defined measurements rather than intuition alone.
- Ability to reason about tradeoffs among latency, cost, and output quality.
- Practical fluency with AI tools and the ability to assess which emerging model capabilities are worth adopting.
Benefits
- Highly competitive cash compensation, equity, and benefits are offered.
- The estimated base salary range for San Francisco or New York City is $255,000–$300,000 per year.
- The role can be based in San Francisco or New York City.
- Employees work from the office on Mondays, Tuesdays, and Thursdays as Anchor Days.
Categories
About Notion
Notion builds an all-in-one workspace that combines docs, wikis, databases, and project management with collaborative AI features for individuals and teams. It operates a freemium, subscription-based, land‑and‑expand model used from small groups to large enterprises. Founded in 2016 and headquartered in San Francisco, the privately held company focuses on unifying knowledge, projects, and workflows in a customizable platform.