Senior GPU Kernel Engineer - Hybrid Triton AI

Advanced Micro Devices; San Jose (CA); Hybrid; USD 180,000 - 280,000; Full time

Job summary

Advanced Micro Devices seeks a highly skilled engineer to advance Triton-based GPU kernels for AI workloads. You will work across Triton/Gluon kernels, PyTorch, vLLM, and ROCm stacks to push performance on AMD Instinct GPUs.

You will partner with researchers, compiler engineers, and hardware teams to design and optimize cutting-edge kernels, improving throughput and efficiency for large-scale AI models while contributing to open-source ecosystems.

Qualifications

• Deep experience in GPU kernel development and AI/ML workloads.
• Hands-on Triton kernels and GPU architectures.
• Strong collaboration across research, compiler, and hardware teams.

Responsibilities

• Design, research, implement, and optimize high-performance matmul, attention (flash, paged, grouped-query), MoE, and fully fused transformer kernels using Triton, targeting large-scale LLM and multimodal workloads.
• Own and productionize critical Triton/Gluon kernels within vLLM and SGL (e.g., paged attention, extend attention, MoE, quantized kernels).
• Partner closely with compiler engineers to develop and maintain the Triton AMD backend across ROCm and the LLVM AMDGPU stack, targeting CDNA and next-generation architectures.
• Drive deep kernel-level optimizations across the AMD memory hierarchy (LDS, L2, HBM), wavefront execution (wave32/wave64), vectorization, MFMA utilization, occupancy tuning, and instruction scheduling.
• Perform rigorous profiling and microbenchmarking led optimization on AMD Instinct GPUs using hardware counters and tracing tools; root-cause bottlenecks in memory bandwidth, latency hiding, synchronization, and register pressure.
• Debug and resolve performance and correctness issues end-to-end across PyTorch, vLLM/SGL runtimes, Triton IR/MLIR, ROCm runtime, and the LLVM AMDGPU backend.
• Contribute to open-source Triton, LLVM, and ROCm ecosystems

Skills

GPU kernel development

Compiler backends

Performance engineering

AI/ML workloads

Education

Bachelor's or Master's degree in CS/CE/EE

Tools

Triton

ROCm

LLVM

SGLang

Torch

MLIR

Job description

Advanced Micro Devices seeks a highly skilled engineer to advance Triton-based GPU kernels for AI workloads. You will work across Triton/Gluon kernels, PyTorch, vLLM, and ROCm stacks to push performance on AMD Instinct GPUs.

You will partner with researchers, compiler engineers, and hardware teams to design and optimize cutting-edge kernels, improving throughput and efficiency for large-scale AI models while contributing to open-source ecosystems.