Senior Deep Learning Systems Architect

NVIDIA is seeking a Senior Deep Learning Systems Architect to help design hardware accelerator and processor architectures that enable state-of-the-art machine learning and data analytics algorithms and applications on next-generation mobile, embedded, and datacenter platforms.

As a member of our deep learning architecture team, you will contribute to features that help next-generation GPUs and systems advance the state of AI.

Responsibilities include:

• Contributing to features that help next-generation GPUs and systems advance the state of AI
• Keeping up with the latest DL research and collaborating with diverse teams, including DL researchers, hardware architects, and software engineers
• Participating in engineering projects and co-designing architecture for systems from conception, specification, and prototyping
• Understanding various AI/DL workloads and their mapping to underlying HW and Systems, identifying potential improvements and bottlenecks, proposing solutions to address existing gaps, and accelerating/improving current systems/methods
• Performing comprehensive analyses from first principles of various deep learning techniques, system optimizations to build out analytical models, implementing prototypes, and benchmarking to test/prove ideas

Requirements:

• MS (or equivalent experience) or PhD degree in computer science, computer architecture, electrical engineering, or related field with 10+ years of relevant work experience
• Strong background in at least a few of the following relevant areas: Machine learning (with focus on Deep Neural Networks), including a solid understanding of DL fundamentals; Experience adapting and training DNNs for various tasks; Experience developing code for one or more of the DNN training frameworks (such as PyTorch, TensorFlow, or JAX); Numerical analysis; Performance analysis and optimization; Computer architecture
• Programming fluency with C++ and ideally Python
• Work experience with GPU computing (CUDA, OpenCL, OpenACC) and HPC (MPI, OpenMP) is a plus

Benefits include equity and standard benefits.