Software Engineer (Model Capabilities)

Join Notion, a leading AI-driven productivity platform. As a Software Engineer on the Model Capabilities team, you'll be at the forefront of AI innovation. Your responsibilities will include integrating frontier models, ensuring reliable and economical inference at scale, and building new capabilities for other teams to utilize. You'll also act as a connector across Notion's AI teams, identifying gaps and facilitating collaboration. Ideal candidates will have experience with production AI systems, a strong understanding of cost and performance trade-offs, and a passion for staying up-to-date with the rapidly evolving AI landscape.

• Integrate frontier models into production quickly, ensuring they are available for users and engineers.
• Enhance inference reliability through better error categorization, self-healing retries, and cross-provider failover.
• Drive down time to detection and time to fix by owning observability for the model layer.

• Measurement before conviction: You don't ship a prompt or model change on vibes. You define what "better" means, build or use the evaluation to test it, and are willing to be proven wrong by your own data
• Cost and performance instincts: You treat latency and dollars as product qualities, not afterthoughts, and you can reason about the tradeoff between them and output quality
• Production AI systems experience: You've built and operated systems on top of LLM APIs, not just prototyped with them. You understand token economics, streaming, tool calling, context limits, and how each of these fails in production
• Comfort with a moving frontier: The model landscape changes monthly. You keep up with it, form your own view of what's real, and stay pragmatic about what's worth adopting now
• AI fluency as a practitioner: You use AI tools seriously in your own work and have opinions about where they help and where they don't