Design, implement, and verify machine learning software for embedded systems running on ARM processors, DSPs, and GPUs in mobile, edge, automotive, and IoT products. Develop optimized ML kernels, compilers, and tools; optimize ML frameworks like TensorFlow and PyTorch for efficient hardware execution. Perform integration, testing, and performance optimization of embedded software subsystems. Collaborate with hardware teams on joint design and development, coordinate cross-team dependencies, and contribute to design reviews.