Machine Learning System Hardware Architect

What you'll do

• Create and evaluate machine-learning system architectures, modeling performance, power, and cost.
• Collaborate with hardware and software teams to optimize the full stack and realize SoC designs.
• Track AI trends and develop partnerships to inform technology roadmaps.

What they ask for

• 5+ years architecting hardware for machine learning, acceleration, and optimization.
• Experience with deep-learning frameworks such as TensorFlow, PyTorch, or PaddlePaddle; CPUs, GPUs, memory systems, and accelerators.
• Experience with C++ performance simulation and modeling, SoC interconnects and NoCs, and area, frequency, and power optimization.
• MS or PhD in Electrical or Computer Engineering; excellent communication skills in English and Chinese.

Nice to have

• Familiarity with video, DSP, Ethernet, and PCIe.
• Strong track record of outreach to ML researchers and application developers.

Tools

TensorFlow, PyTorch, PaddlePaddle, C++, CPUs, GPUs, NoCs, PCIe

AI focus

Architects and optimizes machine-learning silicon and systems, including hardware for distributed AI training.