2 days ago
Base Salary
$124k - $242k/yr
Responsibilities
- Integrate new communication-library features into AI frameworks from proof of concept through performance analysis and production.
- Analyze AI workloads and frameworks to identify multi-GPU communication requirements and opportunities.
- Improve AI compilers to hide communication or perform automatic fusion.
- Conduct performance characterization of AI workloads on multi-GPU clusters.
- Design fault-tolerant and elastic solutions for large-scale or dynamic AI workloads.
- Author custom communication and fused compute-communication kernels for NVIDIA platforms.
- Influence the roadmap of NCCL and NVSHMEM communication libraries.
- Collaborate with teams across multiple time zones.
Requirements
- Bachelor's, master's, or PhD in computer science or a related field, or equivalent experience, with software engineering and HPC/AI experience.
- Development or integration experience with PyTorch, JAX, TRT-LLM, vLLM, or SGLang.
- Rapid prototyping and development experience with Python, C++, CUDA, Triton, cuTe, or related DSLs.
- Understanding of AI models, parallelism, and compiler technologies such as torch.compile.
- Experience benchmarking AI clusters and familiarity with a performance profiler such as PyTorch profiler or NVIDIA Nsight Systems.
- Understanding of HPC/AI communication concepts including one-sided and two-sided communication, elasticity, resiliency, and topology discovery.
- Experience with a communication runtime such as NCCL, NVSHMEM, or MPI is a plus.
- Understanding of computer architecture, hardware-software interaction, operating-system principles, memory hierarchy, consistency models, and tensor layout is valued.
- Expertise in training, distributed inference, mixture-of-experts, reinforcement learning, kernel authoring, compute-communication overlap, or AI compiler pattern matching and lowering is valued.
- Ability to learn new areas and tools and communicate effectively across teams and time zones.
Benefits
- Eligible for equity and benefits.
- Applications will be accepted at least until November 18, 2026.
- This posting is for an existing vacancy.
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.