Senior Accelerated Computing Architect

NVIDIA•Santa Clara, CA

6d•$184,000 - $356,500

About The Position

NVIDIA is developing software and system architectures for accelerated high performance computing, scientific computing, machine learning, AI, datacenter, and automotive computing. This role offers the opportunity to contribute to a fast-moving, technology-focused company by optimizing performance on current and next-generation NVIDIA GPUs and advancing accelerated computing architectures. The architect will collaborate across hardware design, software engineering, product, and research teams, help guide accelerated computing, and communicate work through technical publications and other materials.

Requirements

An MS or Ph.D. in Computer Science, Computer Engineering, or Electrical Engineering, or equivalent experience.
6+ years of relevant work experience.
Strong mathematical fundamentals, including linear algebra and numerical methods.
A passion for performance optimization.
Hands-on experience with massively parallel GPU programming models such as CUDA or OpenCL.
Strong knowledge of C and C++, including software design, programming techniques, and algorithms.
Good communication and organization skills, a logical approach to problem solving, and good time management and task prioritization skills.

Nice To Haves

Familiarity with APIs for multi-node communication, such as MPI or OpenSHMEM/NVSHMEM.
Familiarity with threading APIs for multicore CPUs and Unix-style Inter-process Communication (IPC) APIs.
Familiarity with Python.

Responsibilities

Perform in-depth analysis and optimization to achieve the best possible performance on current and/or next-generation NVIDIA GPUs.
Create and optimize core parallel algorithms, data structures, and reference codes for NVIDIA GPUs.
Analyze how hardware and software architectures interact with core algorithms, programming models, and applications.
Collaborate with hardware design, software engineering, product, and research teams to guide the direction of accelerated computing.
Explore accelerated computing applications to facilitate software-hardware co-design.
Document and present work through white papers, conference publications, official blog posts, patent applications, and other appropriate formats.