Software Development Engineer

• End to end optimization: Build and optimize end to end distributed inference (e.g, P/D disaggregation and Large-EP) and RL solutions on mainstream frameworks like vLLM and SGlang
• Collaborate with GPU Library Teams: Work closely with internal teams to analyze and improve training and inference performance on AMD GPUs
• Collaborate with Open-Source Maintainers: Engage with framework maintainers to ensure code changes are aligned with requirements and integrated upstream
• Work in Distributed Computing Environments: Optimize deep learning performance on both scale-up (multi-GPU) and scale-out (multi-node) systems
• Utilize Cutting-Edge Compiler Tech: Leverage advanced compiler technologies to improve deep learning performance
• Optimize Deep Learning Pipeline: Enhance the full pipeline, including integrating graph compilers
• Software Engineering Best Practices: Apply sound engineering principles to ensure robust, maintainable solutions

• Master’s or PhD in Computer Science, Computer Engineering, Electrical Engineering, or related fields
• 5+ years of professional experience in technical software development, with a focus on GPU optimization, performance engineering, and framework development
• Skilled engineer with strong technical and analytical expertise in C++ development within Linux environments
• Strong problem-solving skills, a proactive approach, and a keen understanding of software engineering best practices
• GPU Kernel Development & Optimization: Deep experienced in designing and optimizing GPU kernels for deep learning on AMD GPUs using HIP, CUDA, and assembly (ASM)
• Strong knowledge of AMD architectures (GCN, RDNA) and low-level programming
• Deep Learning Integration: Strong experienced in integrating optimized GPU performance into machine learning and LLM frameworks (e.g., vLLM, SGlang,TensorFlow, PyTorch)
• End to end solution optimization: Understand the latest market trend of LLM and multimodal, solid hands-on E2E performance tuning experience on distributed inference (e.g, P/D disaggregation and Large-EP) and RL
• Software Engineering: Skilled in Python and C++, with experience in debugging, performance tuning, and test design
• High-Performance Computing: Expert experienced in running large-scale workloads on heterogeneous computing clusters
• Compiler Optimization: Solid understanding of compiler theory and tools like LLVM and ROCm for kernel and system performance optimization

Experienced in Text to Video or Image to Video is a plus

AMD benefits at a glance