Principal Architect, Accelerated Computing

NVIDIA•Us, CA

About The Position

NVIDIA is seeking a Principal Accelerated Computing Architect to develop software and system architectures for accelerated high-performance and scientific computing, machine learning, AI, datacenter, and automotive computing. The position focuses on analyzing and optimizing performance on current and next-generation NVIDIA GPUs, developing core parallel algorithms and data structures, and understanding how hardware and software architectures interact across algorithms, programming models, and applications. The architect will work with hardware design, software engineering, product, and research teams to shape accelerated computing, and will explore applications to support software-hardware co-design. Work may also be documented and presented through white papers, conference publications, official blog posts, and patent applications. The role offers a chance to contribute in a fast-moving, technology-focused company.

Requirements

MS or Ph.D. in Computer Science, Computer Engineering, or Electrical Engineering, or equivalent experience.
12+ years of relevant work experience.
Strong mathematical fundamentals, including linear algebra and numerical methods.
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.
Experience benchmarking, profiling, and characterizing workloads on GPU and CPU clusters.

Nice To Haves

Familiarity with multi-node communication APIs 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 strong performance on current and/or next-generation NVIDIA GPUs.
Create and optimize core parallel algorithms, data structures, and reference code for NVIDIA GPUs.
Analyze the interplay of hardware and software architectures across core algorithms, programming models, and applications.
Lead and collaborate with hardware design, software engineering, product, and research teams to guide accelerated computing direction.
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.
Benchmark, profile, and characterize workloads on GPU and CPU clusters.