Found Description
Join Amazon Devices as a CUDA Kernel Performance Engineer focused on high-performance GPU optimization for edge AI technologies. Deliver peak efficiency in model training and inference workflows.
In the AI Platform team, your role will be crucial in designing and implementing cutting-edge CUDA and Triton kernels. You will work alongside top-tier scientists and engineers to enhance compression algorithms and resolve performance bottlenecks. This position emphasizes your impact on the productivity of the entire team in deploying efficient AI models.
Key Responsibilities:
• Craft efficient CUDA and Triton kernels for edge AI tasks
• Conduct performance optimizations to expedite training processes
• Design profiling and testing infrastructure for kernel efficiency
• Maintain and enhance the training kernels library for ease of use
• Collaborate to unify software and hardware for deployment
Requirements:
• 3+ years of software development experience
• 2+ years ...
In the AI Platform team, your role will be crucial in designing and implementing cutting-edge CUDA and Triton kernels. You will work alongside top-tier scientists and engineers to enhance compression algorithms and resolve performance bottlenecks. This position emphasizes your impact on the productivity of the entire team in deploying efficient AI models.
Key Responsibilities:
• Craft efficient CUDA and Triton kernels for edge AI tasks
• Conduct performance optimizations to expedite training processes
• Design profiling and testing infrastructure for kernel efficiency
• Maintain and enhance the training kernels library for ease of use
• Collaborate to unify software and hardware for deployment
Requirements:
• 3+ years of software development experience
• 2+ years ...
Ready to Apply?
Submit your application for CUDA Kernel Performance Engineer, Amazon AI at Amazon Development Centre Canada ULC
Apply Now