Serve as the primary technical authority for NVIDIA Agent N-S network infrastructure solutions for Chinese CSPs, providing end-to-end consultation on DPU-accelerated API Gateway architecture, Agent traffic routing & orchestration, N-S telemetry, and inline AI inspection pipeline design.
Design and deliver BF4/DOCA 3.0 Agent-specific N-S solutions including: hardware-accelerated Agent API Gateway (replacing Envoy/Nginx software dataplanes), inline token-level Agent traffic metering, multi-agent communication mesh acceleration, and N-S KV-Cache access optimization for disaggregated inference architectures.
Lead open-source network architecture contributions for NVIDIA Agent infrastructure stacks, upstream optimized integrations with cloud-native ecosystems (Kubernetes Gateway API, Envoy xDS, Cilium, eBPF), build China-localized best practices and shape industry technical standards for Agent networking.
Conduct in-depth N-S traffic pattern analysis for Agentic AI workloads (tool-calling, RAG retrieval, multi-agent orchestration, human-agent interaction), implement DPU-level and DOCA-level dataplane optimizations, deliver production-ready reference designs and tuning guidelines for CSP mass deployment.
Act as the key technical liaison between Chinese CSP customers and NVIDIA Networking BU (NBU) global engineering, product and R&D teams, collect high-value local Agent networking requirements, drive BlueField/DOCA product roadmap iteration, and ensure alignment with NVIDIA global technical policies.
Lead technical workshops, hands-on training, PoC and production pilot projects for key CSP accounts, quantify and demonstrate DPU-accelerated Agent networking business value (latency reduction, throughput improvement, TCO savings vs software-only solutions), accelerate technology adoption and large-scale replication.
Monitor cutting-edge industry trends including Agentic AI infrastructure patterns, LLM serving network topology evolution, MCP/A2A protocol standardization, disaggregated inference architecture, and next-gen cloud-native service mesh, output strategic technical insights to support team and product strategy formulation. Mentor junior SA team members on DPU/networking domains, standardize CSP Agent networking technical engagement and solution delivery processes, and drive the precipitation of high-value technical best practices.
What we need to see
Bachelor's/Master's/PhD degree in Computer Science, Computer Engineering, Electrical Engineering, Networking, or a related field; equivalent industry experience is highly valued.
7+ years of hands-on experience in datacenter network architecture, cloud-native networking, DPU/SmartNIC development, or large-scale L4-L7 traffic management systems, with solid experience in North-South dataplane design, API Gateway systems, or service mesh infrastructure.
Deep understanding of datacenter N-S network architecture: load balancing, reverse proxy, API Gateway (Envoy, Nginx, HAProxy), service mesh (Istio, Cilium), and cloud-native networking (CNI, Kubernetes networking model, Gateway API).
Strong programming proficiency in C/C++ and Python; familiar with dataplane programming (DPDK, eBPF/XDP, P4, or DOCA), network protocol stacks (TCP/IP, RDMA, HTTP/2, gRPC), and high-performance packet processing. Proven hands-on experience working with major Chinese CSPs or global hyperscalers on network infrastructure projects, with in-depth knowledge of their cloud networking architecture, traffic management mechanisms, and N-S dataplane evolution. Understanding of AI inference serving architecture (vLLM, TensorRT-LLM, Triton) and how network infrastructure supports inference traffic patterns including: prefill/decode disaggregation, KV-Cache transfer, token streaming, and multi-model Agent orchestration. Excellent technical communication and presentation skills, capable of explaining complex network system and DPU acceleration 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 networking products (BlueField DPU, ConnectX SmartNIC, DOCA SDK, Spectrum switches, NetQ) 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.
Ways to stand out from the crowd
Hands-on experience with BlueField DPU / DOCA dataplane development, including DPA (Data Path Accelerator) programming, hardware steering rules, and crypto/compression offload for N-S traffic.
In-depth experience building or operating large-scale API Gateway / L7 proxy systems at CSP-level traffic volumes (1M+ RPS), with proven optimization for latency-sensitive AI inference traffic. Proven contribution to cloud-native networking open-source projects (Envoy, Cilium, Istio, Kubernetes SIG-Network, or Gateway API) with public upstream records.
Solid understanding of Agentic AI infrastructure patterns: MCP (Model Context Protocol), A2A (Agent-to-Agent) protocol, LangChain/CrewAI/AutoGen runtime architecture, Agent tool-calling traffic patterns, and multi-agent communication topology. Experience designing disaggregated inference serving architectures where network plays a critical role: prefill-decode separation, remote KV-Cache access over RDMA/RoCE, and N-S token routing for mixture-of-experts models.
Familiarity with DPU-based security and observability: inline AI traffic inspection, token-level metering and billing, Agent identity/authentication offload, and zero-trust micro-segmentation for multi-tenant Agent platforms.Proven track record of independently leading CSP network infrastructure PoC, pilot verification and large-scale production deployment projects with measurable business outcomes (latency, throughput, TCO).Familiar with semiconductor and data center technology export compliance requirements in China market.
