23 hours ago
Tel Aviv-Yafo, IsraelSenior
Responsibilities
- Research transport functions, communication semantics, and technologies for optimizing AI workloads and accelerated networking.
- Enhance NVIDIA GPU networking offerings, including NVIDIA Dynamo, NVIDIA NIXL, and NVIDIA UCX, for AI workloads.
- Co-design hardware features in GPUs, DPUs, and interconnects to accelerate data movement, inference, and model serving.
- Lead architecture and design for runtime systems, communication libraries, and AI-specific technologies.
- Identify and evaluate technologies, innovations, and partner relationships against the technology roadmap and business value.
- Lead proof-of-concept development to evaluate and advance new technologies.
- Lead architectural and development efforts involving distributed AI, deep learning, data analytics, HPC, SDN, virtualization, and storage.
Requirements
- Bachelor's, master's, or doctoral degree in computer science, electrical engineering, or computer engineering, or equivalent experience.
- At least 5 years of industry experience, or equivalent, in system architecture, AI systems architecture, AI scaling, parallelism of AI frameworks, or deep-learning training workloads.
- Experience with algorithm design, system programming, computer architecture, operating systems, virtualization, networking, and storage.
- Deep understanding of performance profiling, optimization techniques, and defining and using hardware features.
- Strong programming and software development skills.
- Ability to communicate and work effectively in a multinational, multi-time-zone corporate environment.
- Preferred qualifications include a research track record, experience with CPU/GPU, memory, storage, and networking architecture, and knowledge of deep-learning frameworks and AI communication libraries such as NCCL, UCX, and MPI.
- Preferred experience includes inference and training workload optimization, including Prefill/Decode, data parallelism, tensor parallelism, and FSDP.
Categories
About Nvidia
Nvidia designs and sells GPUs and accelerated computing platforms for data centers, AI/ML, graphics, gaming, and automotive, monetizing through hardware, software platforms (CUDA, AI frameworks), and systems like DGX and networking. Customers include cloud providers, enterprises, researchers, and OEMs. Founded in 1993 and headquartered in Santa Clara, it is a public company traded on NASDAQ under NVDA.