Senior ML Kernel Performance Engineer
Toronto, ONFull Time
AD
Amazon Development Centre Canada ULC
5+ YOECandidates need 5+ years of professional software development, experience leading system design and mentoring engineers, and strong programming skills. Preferred: GPU and accelerator kernel optimization (CUDA, Triton, NKI), LLVM/MLIR, and PyTorch or TensorFlow knowledge.
CUDA, Triton, NKI, PyTorch, TensorFlow, LLVM