Software Engineer Graduate (Inference Infrastructure) - 2026 Start (PhD)

Build and scale cloud-native infrastructure for large-scale LLM inference as part of the Inference Infrastructure team. You’ll design container-based cluster management and orchestration systems for extreme performance, resiliency, and cost efficiency, and architect GPU-optimized AI accelerator infrastructure. Collaborate to deliver inference solutions using vLLM, SGLang, TensorRT-LLM, and stay current with Kubernetes, Ray, and other open-source advances, contributing production-ready code and open-source efforts.