# Senior Solutions Architect, CSP System **Company**: NVIDIA **Location**: Shanghai **Experience**: senior **Job type**: full-time **Category**: Engineering **Industry**: Technology **Apply**: https://nvidia.wd5.myworkdayjobs.com/en-US/NVIDIAExternalCareerSite/job/China-Shanghai/Senior-Solutions-Architect--CSP-System_JR2020192?utm_source=yubhub.co&utm_medium=jobs_feed&utm_campaign=apply **Canonical**: https://yubhub.co/jobs/job_2a721bcf-c6a ## Description As a Senior GPU & AI Infra Expert focusing on Cloud Service Providers (CSPs) in China, you will be a core technical pillar in NVIDIA’s CSP SA team, responsible for driving GPU/AI Infra technical strategy, system-level solution optimization, and high-value customer engagement. You will work closely with major Chinese CSPs to address their critical demands on large-scale AI training/inference, Agentic AI, gaming AI, and distributed computing infrastructure. You will accelerate the mass deployment and performance maximization of NVIDIA GPU software/hardware stacks, and bridge technical gaps between CSP workload iteration and NVIDIA global engineering roadmap. This role requires deep expertise in GPU architecture, AI system optimization, cluster networking, and open-source AI infra contributions, with strong capability to deliver high-value technical outcomes for hyperscale data center workloads. **Responsibilities:** - Partner with Sales, BD and CPM teams to land NVIDIA GPU and AI Infra technologies into top-tier Chinese CSP accounts, drive technical penetration and sustainable business growth. - Serve as the primary technical authority for NVIDIA GPU system and AI infrastructure solutions for Chinese CSPs, providing end-to-end consultation on GPU cluster architecture design, AI workload deployment, heterogeneous computing tuning, and full-stack software stack optimization. - Unlock Vera CPU + GPU co-optimization value for RL training and Agentic AI workloads, eliminate CPU-GPU data movement bottlenecks, optimize end-to-end agent training and reasoning pipeline latency and throughput for CSP AI factory scenarios. - Lead open-source system architecture contributions for NVIDIA AI infra stacks, upstream optimized patches for key open-source projects, build China-localized best practices and shape industry technical standards. - Conduct in-depth GPU workload bottleneck analysis, implement system-level, kernel-level and framework-level tuning for AI training, inference, RL and gaming workloads, deliver production-ready reference designs and tuning guidelines for CSP mass deployment. - Act as the key technical liaison between Chinese CSP customers and NVIDIA global engineering, product and R&D teams, collect high-value local workload requirements, drive product roadmap iteration, and ensure full compliance with NVIDIA global technical policies and export compliance rules. - Lead technical workshops, hands-on training, PoC and production pilot projects for key CSP accounts, quantify and demonstrate GPU/AI Infra business value, accelerate technology adoption and large-scale replication. - Monitor cutting-edge industry trends including Agentic AI, LLM inference optimization, cloud gaming AI, and next-gen data center system architectures, output strategic technical insights to support team and product strategy formulation. - Mentor junior SA team members, standardize CSP technical engagement and solution delivery processes, and drive the precipitation of high-value technical best practices. **Requirements:** - Bachelor’s/Master’s/PhD degree in Computer Science, Computer Engineering, Electrical Engineering, or a related field; equivalent industry experience is highly valued. - 8+ years of hands-on experience in GPU architecture, AI system optimization, large-scale data center infrastructure, or hyperscale cloud computing, with solid experience in AI training/inference, distributed computing or HPC workloads. - Deep understanding of GPU microarchitecture, CUDA programming model, GPU memory hierarchy and system scheduling mechanisms; proficient in performance profiling, bottleneck analysis and end-to-end AI workload tuning. - Strong programming proficiency in C/C++ and Python; familiar with CUDA kernels, compiler toolchains, AI framework optimization (PyTorch/TensorRT) and large-scale distributed system tuning. - Proven hands-on experience working with major Chinese CSPs or global hyperscalers, with in-depth knowledge of their public cloud AI service architectures, cluster operation mechanisms and core workload characteristics. - Excellent technical communication and presentation skills, capable of explaining complex GPU system and AI infra technologies to technical engineers, architecture teams and business stakeholders. - Strong cross-functional collaboration capability, able to work efficiently in a global matrix team and prioritize multiple high-value technical projects under fast-paced business demands. - Familiar with NVIDIA full-stack products (GPU data center hardware, TensorRT-LLM, Dynamo, NCCL, CUDA software stack) is a significant plus. - Hands-on engineering capability is mandatory; candidate must be result-oriented, self-driven and able to independently own end-to-end technical project delivery. - Committed, proactive, and capable of sustaining high-quality technical output for long-term strategic CSP projects. **Benefits:** - Competitive salaries - Generous benefits package ## Skills ### Required - GPU architecture - AI system optimization - large-scale data center infrastructure - hyperscale cloud computing - CUDA programming model - GPU memory hierarchy - system scheduling mechanisms - performance profiling - bottleneck analysis - end-to-end AI workload tuning - C/C++ - Python - CUDA kernels - compiler toolchains - AI framework optimization - large-scale distributed system tuning ### Nice to have - Vera/Grace CPU + GPU heterogeneous co-optimization - AI agent and RL training system tuning - Dynamo LLM inference optimization - KV Cache management - intelligent scheduling planner - dynamic resource scaling - open-source contribution experience in AI infra - GPU optimization libraries - distributed computing frameworks - Agentic AI - RL post-training - long-context LLM workload optimization on GPU clusters - semiconductor and data center technology export compliance requirements in China market --- Source: [Apply at nvidia.wd5.myworkdayjobs.com](https://nvidia.wd5.myworkdayjobs.com/en-US/NVIDIAExternalCareerSite/job/China-Shanghai/Senior-Solutions-Architect--CSP-System_JR2020192?utm_source=yubhub.co&utm_medium=jobs_feed&utm_campaign=apply)