AI Kernel Engineer

Modular is on a mission to revolutionize AI infrastructure by rebuilding the AI software stack. As an AI Kernel Engineer, you will design and optimize high-performance kernels for GPUs, driving performance improvements and enhancing the efficiency of AI applications at scale. Responsibilities: Design and optimize high-performance ML numeric and data manipulation kernels; Benchmark kernel performance and conduct performance analysis; Diagnose performance bottlenecks and implement kernel improvements; Collaborate with framework and compiler teams to deliver end-to-end AI performance that fully utilizes new hardware or GPU capabilities; Ensure kernel correctness, maintainability, and test coverage Qualifications: Experience in GPU programming and parallel computing; Solid understanding of CPU/GPU memory hierarchy and performance modeling; Proficiency in Python or C++; Familiarity with assembly language; Hands-on experience with GPU profiling and debugging tools; Strong foundation in algorithms and data structures; Deep interest in machine learning technologies and use cases; Creativity and curiosity for solving complex problems; A team-oriented attitude that enables you to work well with others; Alignment with our culture Required Skills: GPU programming, Parallel computing, CPU/GPU memory hierarchy, Performance modeling, Python, C++, Assembly language, GPU profiling tools, GPU debugging tools, Algorithms, Data structures, Machine learning technologies, Creativity, Curiosity, Team-oriented attitude