Nvidia Senior Deep Learning Performance Architect Compute Energy Efficiency 

United States, California 

377588406

Develop innovative architectures to extend the state of the art in deep learning performance and efficiency

Prototype key deep learning algorithms and applications

Analyze performance, cost and energy trade-offs by developing analytical models, simulators and test suites

Characterize performance and energy efficiency on scale out systems and work with architecture and systems team to identify and evaluate features to increase at scale efficiency of systems running AI workloads.

Understand and analyze the interplay of hardware and software architectures on future algorithms, programming models and applications

Actively collaborate with software, systems and research teams to guide the direction of deep learning hardware and software

A Masters Degree (or equivalent experience) and 5+ years of meaningful relevant experience or PhD and 2+ years of experience in Computer Science, Electrical Engineering, Computer Engineering, or related field

Good foundation in Deep Learning model architectures and performance tradeoffs

Experience with energy efficient high performance analysis, architecture/system co-design and/or simulation, profiling, and visualizations

Strong programming skills in Python, C, C++

Experience with the parallel computing architectures, or workload analysis on Deep Learning accelerators

Background with GPU Computing and parallel programming models such as CUDA

Experience with deep neural network training, inference and optimization in leading frameworks (e.g. Pytorch, JAX)