GPU Model Optimization Engineer

Responsibilities:

• Performance Analysis and Optimization:Conduct in-depth analysis of GPU applications to identify and resolve performance bottlenecks, focusing on memory access patterns, thread scheduling, and execution efficiency.
• Algorithm Development: Develop efficient GPU-accelerated algorithms using parallel computing frameworks such as CUDA or DirectX to enhance the processing capabilities of computationally intensive tasks.
• Provide technical guidance and training to the team, sharing best practices and optimization techniques in GPU programming.
• Keep abreast of GPU technology and industry trends, evaluating and integrating new technologies to improve system performance.

Requirements:

• Bachelor's or Master's degree in Computer Science, Electrical Engineering, or a related field.
• At least 5 years of experience in GPU programming and performance optimization, familiar with CUDA or DirectX development.
• Proficient in C/C , with in-depth knowledge of computer architecture and parallel computing principles.
• Proficient in using GPU performance analysis and debugging tools, with actual performance optimization achievements.
• Rich experience in performance analysis and tuning of AI/HPC workloads.
• Candidates with practical experience in GPU optimization in fields such as deep learning, computer vision, and scientific computing are preferred.

Plus

• Experience in advanced research or development in the field of High-Performance Computing (HPC) or related areas.
• In-depth understanding of GPU optimization in machine learning frameworks such as TensorFlow or PyTorch.
• Practical experience in deploying and optimizing AI models using Orin and Thor platforms, as well as in developing algorithms related to autonomous driving.
• Practical experience in NVIDIA GPU and CUDA programming.