NVIDIA ยท 5 months ago
Senior Software Architect, AI and HPC
United States
Full-time
Remote
Senior Level
5+ years expNVIDIA is a leader in computer graphics and accelerated computing, now focusing on AI to redefine computing. The role involves researching, developing, and deploying software architecture for AI and high-performance computing systems, including creating proofs-of-concept and enhancing middleware features.
Computer Hardware Manufacturing
Responsibilities
Creating proofs-of-concept to evaluate and motivate extensions in AI Frameworks (PyTorch/NEMO), HPC programming models (MPI, OpenSHMEM, PGAS), new runtime designs, and new network hardware features
Research, design and implement features for AI and HPC communication middleware (NCCL, Open MPI, UCX, UCC, NVSHMEM), and Deep Learning frameworks such as TensorFlow/Pytorch
Review, design, and implement features to enhance compiler features to support the NVIDIA networking ecosystem
Research, design and develop hardware features relevant to scientific, Deep learning, and data-intensive workloads
Qualification
Required
A Ph.D. or Master, in computer science, computer engineering, or a closely related field or equivalent experience
5+ years of experience in parallel programming models, and/or network architecture
Background in algorithm design, system programming, and computer architecture
Strong programming and software development skills
Ability and flexibility to work and communicate effectively in a multi-national, multi-time-zone corporate environment
Deep understanding of technology and passion for what you do
Strong collaborative and interpersonal skills, specifically a proven ability to effectively guide and influence within a dynamic matrix environment
Preferred
Background with designing communication middleware for high-performance computing systems, including InfiniBand, DPUs, Ethernet, and Shared Memory
Experience developing and implementing features for compilers, optimizations for compilers, particularly Clang/LLVM, and NVIDIA compilers
Experience implementing communications libraries, particularly MPI, OpenSHMEM, NCCL, NVSHMEM, UCX, UCC, or PGAS
Background with CUDA programming and NVIDIA GPUs
Programming models for emerging architectures including hierarchical heterogeneous memory systems and accelerators
Benefits
Equity
Benefits
Company
NVIDIA
Since its founding in 1993, NVIDIA (NASDAQ: NVDA) has been a pioneer in accelerated computing.
10,001+ employees
H1B Sponsorship
NVIDIA has a track record of offering H1B sponsorships. Please note that this does not
guarantee sponsorship for this specific role. Below presents additional info for your
reference. (Data Powered by US Department of Labor)
Distribution of Different Job Fields Receiving Sponsorship
Represents job field similar to this job
Trends of Total Sponsorships
2025 (1877)
2024 (1355)
2023 (976)
2022 (835)
2021 (601)
2020 (529)
Funding
Current Stage
Late StageCompany data provided by crunchbase