Senior GPU Performance Engineer - AI Kernel Optimizer

Advanced Micro Devices, Inc.; Santa Clara (CA); On-site; USD 180,000 - 260,000; Full time

Job summary

Advanced Micro Devices, Inc. in Santa Clara, CA, seeks a GPU Performance Engineer to optimize AI workloads and push the performance of AMD Instinct GPUs.

You will analyze kernels, identify bottlenecks, and drive low-level optimizations across multi-node, multi-GPU systems. Collaborating with kernel, compiler, runtime, framework, and distributed systems teams, you will develop benchmarks and microbenchmarks, and communicate findings to drive hardware-software co-design for future AMD

Qualifications

• MS/PhD in CS, CE, or related field.
• Hands-on GPU kernel-level performance analysis and low-level optimization (CUDA/HIP/ROCm).
• Deep GPU microarchitecture knowledge: pipelines, SIMD, memory, interconnects.
• Experience using perf counters, traces, profilers, and ISA/assembly to root-cause bottlenecks.
• Proficient in C++ and GPU kernel programming; Python for automation.
• Linux, Docker, Git/GitHub skills.
• Familiar with AI workloads and frameworks (PyTorch, JAX, Megatron-LM, NCCL/RCCL, MPI).

Responsibilities

• Profile and optimize large-scale AI workloads across multi-node multi-GPU systems.
• Perform deep GPU kernel-level analysis to identify bottlenecks in compute pipelines and memory.
• Root-cause performance gaps using performance counters, traces, ISA/assembly, and microbenchmarks.
• Collaborate with kernel, compiler, runtime, framework, and distributed systems teams to improve performance.
• Develop and maintain benchmarks, microbenchmarks, and traces for foundation model workloads.
• Provide kernel- and microarchitecture-level performance insights to inform hardware/software co-design.

Skills

GPU kernel analysis

Low-level optimization

C++ and GPU kernel programming

Python for performance analysis

Linux

Docker

Git/GitHub

AI workloads familiarity

Education

MS or PhD in CS/CE

Tools

CUDA

HIP/ROCm

Performance counters

ISA/assembly analysis

Microbenchmarks

Reproducer kernels

Job description

Advanced Micro Devices, Inc. in Santa Clara, CA, seeks a GPU Performance Engineer to optimize AI workloads and push the performance of AMD Instinct GPUs.

You will analyze kernels, identify bottlenecks, and drive low-level optimizations across multi-node, multi-GPU systems. Collaborating with kernel, compiler, runtime, framework, and distributed systems teams, you will develop benchmarks and microbenchmarks, and communicate findings to drive hardware-software co-design for future AMD