Cursor Software Engineer on the Model Routing & Inference team building the inference platform powering AI interactions at SpaceXSI. Responsible for building inference gateway, designing failover, and managing traffic routing.
Responsibilities
Build and evolve our inference gateway, a single abstraction over every provider's API semantics, so model onboarding becomes a config change
Design intelligent cross-provider failover so no single provider outage causes user-visible degradation
Design routing backpressure and admission control so traffic spikes don't cascade into providers
Qualification
Experience building high-throughputBachelor's degree in computer scienceADDITIONAL REQUIREMENTSIf there appears to be a fit
Required
Experience building high-throughput, low-latency distributed systems (e.g., inference serving, traffic routing, or real-time data pipelines)
Bachelor's degree in computer science, engineering, math, or scientific discipline; OR 2+ years of professional experience building software in lieu of a degree
Preferred
Comfortable reasoning about cost/performance tradeoffs at scale (GPU utilization, provider economics, capacity planning)
Strong software engineering fundamentals and enjoying shipping production systems that handle millions of requests
ADDITIONAL REQUIREMENTS:
If there appears to be a fit, we'll reach out to schedule 2-3 short technicals. After, we'll schedule an onsite in our office, where you'll work on a small project, discuss ideas, and meet the team
