Found Description
Amazon Devices seeks a CUDA Kernel Engineer to enhance Edge AI through optimized performance. Your expertise will focus on creating high-efficiency kernels for advanced compression algorithms.
As an ML Kernel Performance Engineer, you will design and implement CUDA and Triton kernels that significantly improve model training efficiency. Your role involves collaborating with Applied Scientists and hardware architects to generate solutions that bridge software and hardware, optimizing for both cloud and edge environments.
Key Responsibilities:
• Develop high-performance kernels for model quantization
• Optimize performance using profiling tools
• Implement advanced kernel optimizations
• Collaborate on ML-centric solutions for deployment
• Build and manage performance benchmarking tools
Requirements:
• 3+ years in software development
• 2+ years in system architecture
• Skilled in CUDA kernel programming
• Familiar with Python, Java, C++
• Experienc...
As an ML Kernel Performance Engineer, you will design and implement CUDA and Triton kernels that significantly improve model training efficiency. Your role involves collaborating with Applied Scientists and hardware architects to generate solutions that bridge software and hardware, optimizing for both cloud and edge environments.
Key Responsibilities:
• Develop high-performance kernels for model quantization
• Optimize performance using profiling tools
• Implement advanced kernel optimizations
• Collaborate on ML-centric solutions for deployment
• Build and manage performance benchmarking tools
Requirements:
• 3+ years in software development
• 2+ years in system architecture
• Skilled in CUDA kernel programming
• Familiar with Python, Java, C++
• Experienc...
Ready to Apply?
Submit your application for CUDA Kernel Engineer for Edge AI at Amazon Development Centre Canada ULC
Apply Now