Senior Solutions Architect - CRISP System

Overview

• NVIDIA has been transforming computer graphics, PC gaming, and accelerated computing for more than 25 years.
• It’s a unique legacy of innovation that’s fueled by great technology—and amazing people.
• Today, we’re tapping into the unlimited potential of AI to define the next era of computing.
• An era in which our GPU acts as the brains of computers, robots, and self-driving cars that can understand the world.
• Doing what’s never been done before takes vision, innovation, and the world’s best talent.
• As an NVIDIAN, you’ll be immersed in a diverse, supportive environment where everyone is inspired to do their best work.
• Come join the team and see how you can make a lasting impact on the world.
• At NVIDIA, innovation and excellence fuel our work.
• Our Solutions team seeks a Senior Solutions Architect for our CRISP System-Networking to increase the use of NVIDIA networking products among our clients.
• This is a remarkable opportunity to engage with the latest technology.
• You will work alongside a team of world-class engineers to create the future of computing.
• If you bring proven experience in networking protocols, server I/O, NIC virtualization, and high-performance networking software stacks, this position suits you perfectly! What you'll be doing: Drive technical engagement, solution design, and deployment of NVIDIA networking products , including ConnectX NICs, BlueField DPUs, and related software stacks.
• Understand customer networking requirements across AI, HPC, cloud computing, storage, virtualization, container platforms, and enterprise data centers.
• Design and validate end-to-end network architectures connecting servers, switches, NICs, DPUs, GPUs, and storage systems, from single-node deployments to large-scale clusters.
• Support proof-of-concept projects, cluster bring-up, performance validation, deployment readiness, production issue resolution, and customer acceptance testing.
• Analyze network performance, including throughput, latency, packet loss, congestion, RDMA efficiency, and system bottlenecks.
• Provide architecture and optimization guidance for NIC virtualization, hardware offload, RDMA, RoCE, DPDK, SPDK, Open vSwitch, and related technologies.
• Work closely with NVIDIA product, software, firmware, driver, systems engineering, and sales teams to resolve customer issues and improve solution readiness.
• Collaborate with OEMs, ODMs, switch vendors, server vendors, and software partners on platform compatibility, firmware, BIOS/BMC configuration, PCIe topology, and system validation.
• Develop technical presentations, solution guides, deployment documentation, performance reports, best-practice materials, and customer training content.
• Gather customer requirements and field feedback related to product functionality, performance, interoperability, manageability, and deployment challenges.
• What we need to see: 5 years above working experience and Bachelor's degree in Engineering, Computer Science, or comparable experience.
• Strong knowledge of NICs, DPUs , and their hardware architecture, capabilities, deployment models, drivers, firmware, and diagnostic tools.
• Solid understanding of SmartNIC/DPU offload technologies, including RDMA, RoCE, TCP/UDP offload, overlay offload, encryption offload, virtual switching offload, and flow-processing acceleration.
• Strong knowledge of Ethernet and data center networking protocols, including L2/L3 forwarding, VLAN, VXLAN, , TCP/IP, UDP, ARP, IPv6, MTU, and Jumbo Frames.
• Familiarity with network virtualization and acceleration technologies, including SR-IOV, VirtIO, vDPA, PCIe passthrough, IOMMU, PF/VF, RSS, RPS, XPS, DPDK, SPDK, Open vSwitch, and OVS-DPDK.
• Familiarity with virtualization and cloud-native networking environments, including KVM, VMware, Kubernetes, CNI, Multus, SR-IOV CNI, OpenStack Neutron, OVN, and NFV.
• Familiarity with server platform technologies, including BIOS, BMC, UEFI, Redfish/IPMI, Secure Boot, firmware lifecycle management, system bring-up, and hardware compatibility validation.
• Ways to stand out from the crowd: Hands-on experience with lossless Ethernet and congestion-management technologies, including QoS, PFC, ECN, DCQCN, traffic shaping, queue management, and congestion control.
• Experience designing, deploying, and troubleshooting Leaf-Spine, Clos, L2/L3 Fabric, AI cluster, RoCE, or InfiniBand network topologies.
• Familiarity with NVIDIA's networking and GPU technology.
• Strong leadership and project management skills.
• Excellent communication skills and ability to work across diverse teams.
• Join us and be part of a team that’s defining the next era of computing!.