AI Framework and Performance Experts(vLLM, SGLang)
Beijing, ChinaFull-timePosted 2mo ago
About the role
Role focused on optimizing and developing deep learning frameworks and GPU kernels for AMD GPUs, collaborating across teams and with open-source communities to accelerate AI training and inference at scale.
Responsibilities
- Optimize Deep Learning Frameworks: Enhance performance of frameworks like TensorFlow, PyTorch, and SGLang on AMD GPUs via upstream contributions in open-source repositories.
- Develop and Optimize Deep Learning Models: Profile and tune large-scale training and inference models for optimal performance on AMD hardware.
- GPU Kernel Development: Design, implement, and optimize high-performance GPU kernels using HIP, Triton, or other relevant tools for AI operator efficiency.
- Collaborate with GPU Library and Compiler Teams: Work closely with internal compiler and GPU math library teams to integrate and align kernel-level optimizations with full-stack performance goals.
- Contribute to SGLang Development: Support optimization, feature development, and scaling of the SGLang LLM framework across AMD GPU platforms.
- Distributed System Optimization: Tune and scale performance across both multi-GPU (scale-up) and multi-node (scale-out) environments, including inference parallelism and collective communication strategies.
- Graph Compiler Integration: Integrate and optimize runtime execution through graph compilers such as XLA, TorchDynamo, or custom pipelines.
- Open-Source Collaboration: Partner with external maintainers to understand framework needs, propose optimizations, and upstream contributions effectively.
- Apply Engineering Best Practices: Leverage modern software engineering practices in debugging, profiling, test-driven development, and CI integration.
Qualifications
- Bachelor’s and/or Master’s Degree in Computer Science, Computer Engineering, Electrical Engineering, or a related field.
- Strong Programming Skills: Expert in C++ and/or Python, with demonstrated ability to debug, profile, and optimize performance-critical code.
- SGLang and LLM Optimization: Solid hands-on experience with SGLang or similar LLM inference frameworks is highly preferred.
- Compiler and GPU Architecture Knowledge: Background in compiler design or familiarity with technologies like LLVM, MLIR, or ROCm is a plus.
- Heterogeneous System Workloads: Expert experience running and scaling workloads on large-scale, heterogeneous clusters (CPU + GPU) using distributed training or inference strategies.
- AI Framework Integration: Strong experience and contribution to or integrating optimizations into deep learning frameworks such as PyTorch or TensorFlow.
- GPU Computing: Solid and strong knowledge of HIP, CUDA, or other GPU programming models; experience with GCN/CDNA architecture preferred.
Skills
Required:C++HIP/CUDA
Nice to have:PythonSGLangLLVM/MLIR/ROCm
Benefits
- Benefits offered are described: AMD benefits at a glance.
Last updated Oct 15, 2026. Interested? Apply on the company site.
About AMD
together we advance_AI
AMD delivers leadership high-performance and adaptive computing solutions to advance data center AI, AI PCs, intelligent edge devices, gaming, & beyond.
AIData CenterHigh-Performance ComputingGamingEdge Devices
More open roles at AMD
- System Thermal Design Staff Engineer4d agoPenang, Malaysia · Engineering
- PD Engineer4d agoHybrid (Bangalore) · Engineering
- PD Engineer4d agoBangalore · Engineering
- Low-Power & CDC Verification Engineer4d agoSanta Clara, California · Engineering
- Technical Program Manager4d agoShanghai · Engineering