Principal Deep Learning Communication Architect
NVIDIA· Architect
Hybrid (US: Santa Clara, CA / Austin, TX / Remote)$272k - $431.3kfull-timePosted 6mo ago
About the role
NVIDIA seeks a Principal Deep Learning Communication Architect to define long-term roadmaps for AI/ML communication libraries, lead development of next-generation primitives and algorithms, co-design with applications and hardware teams, and build analytical models to predict system behavior for trillion-parameter AI workloads.
Responsibilities
- Architecture Leadership: Define the long-term technical roadmap for communication libraries across NVIDIA’s next-generation platforms. Ensure seamless scaling of models to clusters with hundreds of thousands of nodes.
- AI Communication Library Design: Lead the development of next-generation communication primitives and collective algorithms, optimizing for heterogeneous interconnects (NVLink, Spectrum-X, Quantum-X).
- Application-Communication Library Co-Design: Partner with application developers to architect and implement specialized communication primitives for AI and HPC libraries (NCCL, NIXL, NVSHMEM, UCC, UCX) to meet trillion-parameter and Agentic AI requirements.
- Hardware/Software Co-Design: Collaborate with silicon architects and software engineers to influence hardware specs for next-generation networking to support trillion-parameter LLMs and Agentic AI.
- Quantitative Modeling: Develop high-fidelity analytical models and simulators to predict system behavior under emerging workloads.
Qualifications
- Ph.D. or M.S. in Computer Science, Electrical Engineering, or a related field (or equivalent experience), with 12+ years of industry HPC or distributed deep learning experience.
- Parallelism Expertise: Deep understanding of 3D parallelism (Data, Tensor, Pipeline) and advanced strategies including Context Parallelism, Expert Parallelism, and ZeRO variants.
- Technical Proficiency: Proficiency with NCCL, UCX, UCC, NVSHMEM, or MPI. Experience with RDMA, RoCE, and low-level InfiniBand verbs.
- Inference & Serving: Advanced knowledge of high-throughput inference engines and schedulers (TensorRT-LLM, vLLM, SGLang, NVIDIA Dynamo).
- GPU Architecture: Expert knowledge of NVIDIA GPU memory hierarchy (HBM3e/HBM4, L2 cache) and CUDA programming models.
Skills
Required:3D parallelism (Data, Tensor, Pipeline)NCCLUCXUCCNVSHMEMRDMA/RoCEInfiniBand verbsTensorRT-LLMvLLMSGLangNVIDIA DynamoCUDAGPU memory hierarchy
Nice to have:MPIMegatron-Core/DeepSpeed/JAX/XLA
Benefits
- Equity
- Benefits package (as described in NVIDIA benefits)
Last updated Jul 3, 2026. Interested? Apply on the company site.
About NVIDIA
World Leader in AI Computing
NVIDIA invents the GPU and drives advances in AI, HPC, gaming, creative design, autonomous vehicles, and robotics.
AIautonomous vehiclesgaminggpugraphics cardhigh performance computingliquid-ai-recruiting-targetllm
More open roles at NVIDIA
- Senior Physical Verification Engineer3d agoEngineer, ASIC
- Senior System Software Engineer, Display Security3d agoEngineer, Sys SW
- Senior FPGA Prototyping Engineer - Hardware3d agoSanta Clara, CA · Engineer, ASIC
- Senior Product Engineer3d agoHybrid (Thailand) · Engineer, Product Development
- Senior Architect - Data Processing Systems, Analytics and Data Intelligence3d agoHybrid (Remote / Local) · Architect