Share
Partner with multi-disciplinary teams to design, implement, and verify performance metrics for NVIDIA GPUs
Work on developing and improving methodologies for profiling data collection from GPUs
Define, invent, and improve our GPU profiling library with new features to allow NVIDIA's customers to extract the best performance out of their applications
Read and understand HW specs to design solutions based on it
Work on software unit level tests and framework ensuring the quality of the product
Work on supporting a variety of platforms ranging from super-computers to embedded systems
B.Tech. EE/CS or equivalent with 4+ years of experience, or M.Tech. with 2+ years of experience, or Ph.D.
Strong programming ability in C, C++, Python with proficiency in Data Structures and Algorithms
Solid understanding of Computer Architecture (e.g. x86, ARM CPUs, GPUs) and Operating System concepts
Knowledge of SW design principles, as that's a key as we scale!
Experience in Device Drivers or System Software development
Knowledge of GPU APIs such as CUDA, OpenCL, OpenGL, Direct3D, Vulkan
Prior experience authoring developer tools, particularly for GPUs
Experience in performance analysis of GPU applications
Ability to read and write in Assembly language, especially for multi-processor architectures
These jobs might be a good fit