Software Engineer - AI Compute Infrastructure

Build and operate cloud-native infrastructure for large-scale LLM inference in ByteDance’s Inference Infrastructure team. Design high-performance, scalable container-based cluster management and GPU/AI accelerator orchestration systems, and integrate next-gen inference solutions using vLLM, SGLang, and TensorRT-LLM. Stay current with open source (Kubernetes, Ray) and AI/ML systems research, writing production-ready code for resilient, cost-efficient ML platforms.