Senior GPU Kernel Engineer for AI and LLM Workloads

Advanced Micro Devices, Inc.; San Jose (CA); Hybrid; USD 150,000 - 190,000; Full time

Benefits offered by this job

AMD Benefits

Job summary

Advanced Micro Devices, Inc. (AMD) seeks a senior technical member to design, develop, and optimize high-performance GPU kernels for LLMs and ML models. You will analyze bottlenecks, drive architecture-aware optimizations, and collaborate with architecture, compiler, and framework teams to improve GPU performance.

You will lead performance analyses and contribute to portable, scalable GPU software, leveraging LLVM/MLIR and related tools for next‑generation compute platforms.

Qualifications

• Bachelors or Masters degree in electrical or computer engineering.
• Strong C++ programming skills and deep understanding of GPU compute and memory hierarchies.
• Experience building and optimizing GPU kernels using HIP/CUDA, with performance profiling and bottleneck removal.
• Familiarity with compiler/code-generation tech such as LLVM/MLIR is a plus.
• Ability to lead projects independently within a high-performing team.

Responsibilities

• Architect and optimize AI workloads, including LLMs and emerging models.
• Design, implement, profile, and optimize GPU kernels for AMD architectures.
• Perform deep performance characterization across compute, memory bandwidth, and cache hierarchy to remove bottlenecks.
• Develop compiler-level optimizations and code-generation techniques using LLVM/MLIR.
• Apply AI techniques to create next-generation tools for code generation and performance analysis.

Skills

C++

GPU architecture

GPU kernels

HIP/CUDA

Performance analysis

Education

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

Tools

LLVM

MLIR

Job description

Advanced Micro Devices, Inc. (AMD) seeks a senior technical member to design, develop, and optimize high-performance GPU kernels for LLMs and ML models. You will analyze bottlenecks, drive architecture-aware optimizations, and collaborate with architecture, compiler, and framework teams to improve GPU performance.

You will lead performance analyses and contribute to portable, scalable GPU software, leveraging LLVM/MLIR and related tools for next‑generation compute platforms.