As the manager in this role, you will support a dynamic team of engineers, with skills that range from machine learning and frameworks like PyTorch and MLX, to deep compiler expertise in MLIR and LLVM. You will partner with other leaders across the organization and company to both develop our platform as well as support clients internally and externally. The role requires a deep technical understanding of ML research→production workflows, ML compilations, runtimes, and on-device optimization techniques (such as quantization, distillation, etc.).