Cursor07.04.2026
Software Engineer, Model Routing & Inference
Полная занятостьОфис
Обязанности
- 01Build the inference platform that powers every AI interaction in the product
- 02Own the full inference path: making AI faster, more reliable, and more cost-effective
- 03Build and evolve the inference gateway, a single abstraction over every provider's API semantics
- 04Design intelligent cross-provider failover
- 05Design routing backpressure and admission control
Требования
- 01Deep experience building high-throughput, low-latency distributed systems, especially in inference serving, traffic routing, or real-time data pipelines
- 02Comfortable reasoning about cost/performance tradeoffs at scale (GPU utilization, provider economics, capacity planning)
- 03Strong software engineering fundamentals and enjoy shipping production systems that handle millions of requests
- 04Make good calls in the gray area: weighing reliability, cost, latency, and user experience