Senior Applied Power Architect - GPU

Responsibilities

• You will be responsible for inventing methodologies, features and techniques to address electrical/speed/power challenges for NVIDIA's next generation AI architectures such as Rubin and Feynman.
• Drive power management initiatives to optimize power efficiency and performance, while addressing electrical/thermal and power constraints.
• Understand process characteristics and its impact of V-F and drive analysis of various V-F tradeoffs considering Vt choices on power/other metrics and overall performance.
• Investigate multi-die technologies and come up with innovative solutions to address packaging, interconnect, physical design, electrical and thermal challenges.
• Analyze peak current, Di/Dt, IR and EM requirements, and collaborate closely with ASIC designers, Power Integrity, Packaging experts and Product engineers to understand challenges and formulate solutions.
• What we need to see
• MSEE/MSCE, preferably PhD, or equivalent experience with a specialization in low-power-processor architectures.
• Solid understanding of energy efficient system design fundamentals, performance/power modeling and related tradeoffs from your 6+ years of relevant industry experience.
• A background in PDN design and good understanding of electrical issues such as Di/Dt, undershoot/overshoot, IR, EM, peak current, analysis/mitigation techniques are helpful.
• Exposure and working knowledge of Python and data analysis packages like: Pandas, NumPy, PyTorch is a plus.

Languages