← All roles

Principal Architect, AI Inference Networking - NIXL and Dynamo

NVIDIA· Architect
Apply on company site
Shanghai, Shenzhenfull-timePosted 4w ago

About the role

Senior architect role focusing on NIXL adoption and integration with NVIDIA Dynamo in China, driving hardware-accelerated AI inference networking, API design for elastic data paths, and upstream contributions.

Responsibilities

  • Drive NIXL adoption in China, from the first architecture conversation through prototype and benchmark to production rollout and upstream contribution.
  • Profile customer inference stacks and fix throughput and TTFT bottlenecks: KV cache movement, memory registration, transfer scheduling.
  • Write NIXL backends and plugins, extend Dynamo integrations, and contribute optimizations upstream to NIXL and GPUDirect class data paths.
  • Help define APIs that enable dynamic data paths, supporting elastic scaling, worker churn and runtime rerouting in production inference clusters.
  • Bring the region's requirements into NVIDIA's roadmap with technical authority.
  • Grow the local community around NIXL through talks, benchmarks and reference architectures.

Qualifications

  • M.Sc. or Ph.D. in CS/EE/CE, or equivalent depth earned in industry.
  • 12+ years building or optimizing large scale distributed systems: AI inference or training infrastructure, communication libraries, high performance networking, or HPC runtimes.
  • Strong systems programming in C++ and Python, with performance critical code shipped.
  • Hands on experience with RDMA networking (InfiniBand or RoCE) and GPU memory movement.
  • Working knowledge of modern LLM serving, including prefill/decode disaggregation, KV cache management, tensor and pipeline parallelism, and at least one serving stack (Dynamo, TensorRT-LLM, vLLM, SGLang, Triton).
  • Strong communication skills, with the technical credibility to be taken seriously by customer engineering teams and by NVIDIA's core library maintainers.
  • Fluent Mandarin and professional English, and comfortable working across China, Israel and US time zones.

Skills

Required:C++PythonRDMA networkingGPU memory movementLLM serving knowledgeCommunicationMandarin

Benefits

  • N/A provided in description – not listed; include if available by source
Last updated Sep 25, 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
Company profileWebsite

More open roles at NVIDIA