Senior Software Engineer, ML Compiler, TPU

Job description

Deliver compiler parallelization features and optimization techniques for TPU backend necessary for large-scale workloads. Contribute to collective operation lowering/implementation on TPU platform. Develop compiler optimization techniques at lower level and throughout the compiler stack. Analyze upcoming and existing features in TPU architectures and leverage them for most optimal horizontal scaling performance. Build compiler related tools for debugging and preventing scaling issues and improving engineering experience. Minimum Qualifications: Bachelor's degree in Computer Science, or a related technical field, or equivalent practical experience. 5 years of experience with software development in one or more programming languages, including Python and C++. 3 years of experience with Machine Learning infrastructure, ML execution frameworks (e.g., TensorFlow, JAX, PyTorch), or hardware accelerators (e.g., TPUs, GPUs). 2 years of experience in a low level systems programming language (e.g., C++). Experience in performance and compilers. Preferred Qualifications: 3 years of experience in low level ML accelerator programming, compiler or other close to hardware performance programming. Experience in profiling workloads, identifying and introducing performance optimization. Experience in high-performance and readable c++. Experience in hardware design and hardware architecture. Working knowledge of machine learning compilers (e.g., XLA or MLIR) and experience co-designing hardware-aware optimizations to accelerate model execution.