Senior GPU Kernel Development Engineer
Core
Design, develop, and optimize high-performance GPU kernels for LLMs and ML models to maximize compute efficiency and memory bandwidth.
Role type
Senior IC GPU kernel development engineer
Builds
High-performance GPU kernels and compiler-level optimizations for AMD GPU architectures
Domain
Semiconductor / AI / High-performance computing
Deliverable
production ML models
Required skills
C++, GPU programming, performance analysis, system software development, architecture-aware optimization
Preferred skills
HIP, CUDA, memory hierarchy understanding, cache behavior, kernel scheduling, AI-assisted development tools
Technologies
HIP, CUDA, LLVM, MLIR
Responsibilities
Architect and optimize AI workloads (LLMs, quantized models); Develop and profile high-performance GPU kernels; Drive deep performance characterization (compute, memory, cache); Advance compiler and code-generation technologies; Innovate with AI-assisted development tools
Seniority
Senior, hands-on IC
