Senior Machine Learning Software Engineer, GPU Acceleration, Silicon

Google's software engineers develop the next-generation technologies that change how billions of users connect, explore, and interact with information and one another

• Design and implement optimized GPU kernels for compute-intensive workloads
• Enhance machine learning model inference performance on mobile Graphics Processing Unit (GPU) architectures
• Implement novel machine learning-based algorithms to advance GPU graphics rendering capabilities
• Conduct system-level performance analysis, identify bottlenecks, and implement optimizations across the hardware/software stack

• Bachelor's degree in Computer Science, Electrical Engineering, a related technical field, or equivalent practical experience
• 5 years of experience in software engineering with performance-critical systems or low-level development
• Experience with on-device machine learning
• Experience with programming in C and C++
• Preferred qualifications: Experience with GPU programming (e.g., CUDA, OpenCL, Metal, Vulkan Compute)
• Preferred qualifications: Experience in designing, implementing, and optimizing machine learning models using frameworks like TensorFlow or PyTorch
• Preferred qualifications: Experience with performance analysis, profiling, and debugging tools for mobile devices
• Preferred qualifications: Knowledge of computer architecture with mobile systems on a chip (SoC) architectures and GPU pipelines

• Experience with on-device machine learning
• Experience with programming in C and C++
• Experience with GPU programming (e.g., CUDA, OpenCL, Metal, Vulkan Compute)
• Experience in designing, implementing, and optimizing machine learning models using frameworks like TensorFlow or PyTorch
• Experience with performance analysis, profiling, and debugging tools for mobile devices
• Knowledge of computer architecture with mobile systems on a chip (SoC) architectures and GPU pipelines

Google's mission is to organize the world's information and make it universally accessible and useful