Senior GPU Kernel Engineer for AI & LLM Workloads

AMD; San Jose (CA); On-site; USD 180,000 - 230,000; Full time

Job summary

AMD is seeking a senior technical contributor to design, develop, and optimize high‑performance GPU kernels for LLMs and ML models. You will analyze bottlenecks and craft architecture‑aware optimizations to boost compute efficiency and memory bandwidth while collaborating with architecture, compiler, and framework teams.

The role requires leadership, guiding teams and driving initiatives independently, with education in electrical or computer engineering and strong C++/GPU experience.

Qualifications

• Strong experience in GPU programming and performance analysis.
• Provide technical leadership and drive projects independently.
• Define goals, scope, and own development efforts within a high‑performing team.

Responsibilities

• Architect and optimize AI workloads for AMD GPU architectures.
• Develop high‑performance GPU kernels and profile for hardware utilization.
• Perform deep performance characterization across compute, memory, and scheduling to remove bottlenecks.
• Advance compiler and code‑generation tech using LLVM/MLIR for portability.
• Explore AI‑assisted tools to improve development productivity.

Skills

Strong C++ skills

GPU compute understanding

Performance bottlenecks analysis

Self-starter independent drive

Education

Bachelor's or Master's degree in electrical or computer engineering

Tools

HIP

CUDA

C/C++

LLVM/MLIR

Job description

AMD is seeking a senior technical contributor to design, develop, and optimize high‑performance GPU kernels for LLMs and ML models. You will analyze bottlenecks and craft architecture‑aware optimizations to boost compute efficiency and memory bandwidth while collaborating with architecture, compiler, and framework teams.

The role requires leadership, guiding teams and driving initiatives independently, with education in electrical or computer engineering and strong C++/GPU experience.