Software Engineer - AI Compute Infrastructure

Build and operate cloud-native, GPU-optimized inference infrastructure for large-scale LLM workloads. You’ll design container-based cluster management and orchestration systems, architect secure and cost-efficient GPU/AI accelerator platforms, and collaborate on inference solutions using vLLM, SGLang, and TensorRT-LLM. Work in a hyper-scale environment, integrate advances from Kubernetes/Ray and ML systems research, and contribute production-ready, maintainable code.