Applied AI Inference Engineer

Baseten, which powers production AI inference for companies like Cursor, Notion and Writer (and recently raised a $300M Series E), is hiring an Applied AI Inference Engineer. You would partner directly with customers to architect, build and deploy high-scale production AI applications on Baseten's platform, owning the journey from exploration to production with clear latency, quality and cost outcomes. It is explicitly a hands-on engineering role with product-management, technical-customer-success and pre-sales solution-engineering mixed in. Day to day means turning vague objectives into well-tested services, mostly in Python, deploying model servers from Docker images and exposing workflows as APIs. Requirements are light on years (1+ years) but expect real familiarity with AI/ML pipelines and the model deployment lifecycle. The differentiator is the front-row seat: you see how the fastest-moving AI companies actually take models to production, across the full sales-to-expansion arc.