Elevate your career as a GPU Kernel Optimization Engineer at Baseten, where your work accelerates AI model performance. Collaborate with dynamic teams to shape groundbreaking technology.
This role at Baseten involves crafting high-performance GPU kernels essential for machine learning operations. You will be responsible for optimizing every microsecond of computation using advanced techniques, contributing to impactful AI applications. The position is perfect for engineers who excel in low-level optimization and aspire to influence AI innovations.
Key Responsibilities:
• Implement GPU kernels for complex ML operations
• Optimize code performance using CUDA and PTX assembly
• Apply cutting-edge features like quantization and sparsity
• Troubleshoot performance issues using industry-standard tools
• Present technical findings at major conferences
Requirements:
• Strong grasp of GPU programming paradigms
• Experienced in C++ and profiling GPU performance
• Knowledge of memory access patterns and bandwidth optimization
• Familiarity with modern GPU features like tensor cores
• Contributions to GPU-related open-source projects a plus
Join Baseten to redefine the future of AI through your expertise in GPU optimization.
#J-18808-Ljbffr