Senior RDMA and Networking Architect

At NVIDIA, we are building the networking technologies behind the world’s most demanding AI, cloud, and high-performance computing platforms. RDMA, congestion management, and multipath transport are central to that work, shaping protocol behavior, interoperability, reliability, and end-to-end performance at scale. We are looking for a senior architect or technical leader with deep expertise in networking protocols and the broader interconnect ecosystem to help define the next generation of capabilities across our platforms. This role is ideal for someone who combines strong protocol knowledge with architectural judgment, product sense, and credibility in industry forums. You may come from protocol architecture, NIC or switch design, systems research, or standards leadership, but in all cases you know how to turn technical insight into roadmap impact. In this role, you will work across architecture, hardware, firmware, software, product, and ecosystem partners to shape protocol direction, influence standards, and drive implementable innovation. If you want to help define the future of RDMA and AI networking, we’d love to hear from you!
What you'll be doing:
Define and guide protocol and architecture direction for RDMA and sophisticated transport technologies across next-generation networking platforms, with particular focus on performance, scalability, interoperability, and adaptability.
Lead technical work spanning RDMA semantics, congestion management, multipath transport, reliability, ordering, virtualization, and software-visible interfaces.
Develop NVIDIA's viewpoint and contributions across major ecosystem and standards organizations, including UEC, IBTA, IEEE, and OCP.
Work closely with architects, hardware, firmware, software, validation, and product teams to transform protocol concepts into practical features and prioritized roadmap investments.
Evaluate standards proposals, protocol extensions, and ecosystem requirements; identify tradeoffs early and drive streamlined technical recommendations.
Engage with contributors from inside and outside the organization to advance interoperability, performance portability, and adoption within the RDMA ecosystem.
Use analysis, modeling, experimentation, traces, and system-level reasoning to validate architectural decisions and expose bottlenecks or protocol gaps.
Represent the technical direction of the work clearly to senior leaders, engineering teams, and external collaborators.
What we need to see:
B.Sc, M.Sc, or PhD in Computer Science, Electrical Engineering, Computer Engineering, or equivalent experience.
More than 10 years of proven experience in networking protocols, interconnect architecture, systems research, or related areas.
Strong technical knowledge in one or more fields such as RDMA technologies (InfiniBand, RoCE, verbs and transport semantics), NIC or switch architecture, congestion control algorithms, or multipath transport.
Strong understanding of modern data center networking, including Ethernet, congestion management, routing and switching interactions, and large-scale system behavior.
Proven background in protocol definition, contributing to standards, interoperability efforts, or technical leadership within an ecosystem.
Ability to reason across hardware, firmware, software, and system architecture boundaries and make well-grounded technical tradeoffs.
Strong record of influencing technical direction across multi-functional teams and aligning diverse collaborators around architecture decisions.
Strong interpersonal skills, including the ability to convey complex technical perspectives clearly in both internal and external environments.
Ways to stand out from the crowd:
Experience engaging in or leading initiatives in UEC, IBTA, IEEE, OCP, or comparable industry standards and ecosystem organizations.
Expertise in SmartNICs, DPUs, NIC architecture, switch architecture, or hardware/software co-design for sophisticated networking systems.
Deep background in congestion control — algorithm development, analysis, simulation, or deployment at scale in data center or HPC environments.
Experience with multipath transport protocols, load balancing, or adaptive routing across large-scale fabrics.
Familiarity with GPU networking, GPUDirect RDMA, collective communication patterns, or AI and HPC workload behavior over RDMA fabrics.
NVIDIA is committed to fostering a diverse work environment and is proud to be an equal opportunity employer. As we highly value diversity in our current and future employees, we do not discriminate (including in our hiring and promotion practices) on the basis of race, religion, color, national origin, gender, gender expression, sexual orientation, age, marital status, veteran status, disability status or any other characteristic protected by law.
We will ensure that individuals with disabilities are provided reasonable accommodation to participate in the job application or interview process, perform essential job functions, and receive other benefits and privileges of employment. Please contact us to request an accommodation.