About the job
NVIDIA is looking for outstanding Performance Architects with a background in performance analysis, performance modeling, and AI/deep learning to help analyze and develop the next generation of architectures that accelerate AI and high-performance computing applications.
Responsibilities
Develop innovative architectures to extend the state of the art in deep learning performance and efficiency
Analyze performance, cost and power trade-offs by developing analytical models, simulators and test suites
Understand and analyze the interplay of hardware and software architectures on future algorithms, programming models and applications
Develop, analyze, and harness groundbreaking Deep Learning frameworks, libraries, and compilers
Actively collaborate with software, product and research teams to guide the direction of deep learning HW and SW
Qualifications
Minimum
MS or PhD in Computer Science, Computer Engineering, Electrical Engineering or equivalent experience
6+ years of meaningful work experience
Strong background in GPU or Deep Learning ASIC architecture for training and/or inference
Experience with performance modeling, architecture simulation, profiling, and analysis
Solid foundation in machine learning and deep learning
Strong programming skills in Python, C, C++
Preferred
Background with deep neural network training, inference and optimization in leading frameworks (e.g. Pytorch, JAX, TensorRT)
Experience with relevant libraries, compilers, and languages - CUDNN, CUBLAS, CUTLASS, MLIR, Triton, CUDA, OpenCL
Experience with the architecture of or workload analysis on other DL accelerators
Demonstration of self-motivation, with a knack for critical thinking and thinking outside the box