Principal Technology Role

BroadcomSan Jose, CA

About The Position

We are seeking a Principal Technology Leader to drive the architecture, strategy, and ecosystem engagement for next-generation AI networking and infrastructure solutions. This role operates horizontally across business units, shaping cohesive end-to-end (E2E) system architectures spanning GPU/XPU compute, networking fabrics, memory systems, and software stacks. The candidate will engage deeply with hyperscalers, AI platform providers, and silicon partners, influencing both product direction and industry standards, while translating workload requirements into scalable, high-performance infrastructure designs. Broadcom is a global technology leader that designs, develops and supplies a broad range of semiconductor and infrastructure software solutions.

Requirements

  • Bachelor's degree in Engineering field and 15+ years of experience in: Networking architecture (Ethernet switching, NICs, transport protocols) Large-scale distributed systems or HPC/AI infrastructure
  • Deep expertise in: AI/ML workloads (training & inference) Scale-up and scale-out network architectures Congestion control, transport protocols, and performance optimization
  • Strong understanding of: GPU/XPU architectures and communication patterns Memory systems (HBM, CXL, KV cache architectures)
  • Proven experience working with hyperscalers or large cloud providers
  • Demonstrated ability to influence product strategy and architecture at scale

Nice To Haves

  • Experience with: Ultra Ethernet / RDMA / RoCE / custom AI transports High-radix switching architectures and topology design Optical interconnects (pluggables, LPO, CPO)
  • Active participation in industry standards bodies (OCP, UEC, IEEE)
  • Track record of: Publications, patents, or conference presentations
  • Driving cross-organizational initiatives

Responsibilities

  • Cross-BU Technical Leadership Work across switching, NIC, optics, and software BUs to: Align on a unified AI networking strategy Influence roadmaps and feature prioritization Ensure architectural consistency across product lines Act as a technical bridge between silicon, systems, and software teams Identify gaps and drive new product/feature incubation
  • Customer & Partner Engagement Serve as a trusted technical advisor to key customers: Hyperscalers AI infrastructure providers GPU/XPU vendors Engage in deep co-design discussions on: Cluster architectures Networking topologies (Clos, Dragonfly, multi-plane scale-up) Congestion control and transport behavior Translate customer requirements into actionable architectural and product inputs Support executive-level technical discussions and strategic engagements
  • AI Networking Strategy & Industry Leadership Define and drive long-term AI networking strategy, including: Ethernet evolution for AI (lossless, low-latency enhancements) Scale-up networking over Ethernet (e.g., SUE, ESUN concepts) Integration with emerging standards (UEC, OCP, IEEE) Represent the company in: Industry consortia (OCP, UEC, IEEE) Technical conferences (SC, Hot Chips, etc.) Develop thought leadership: whitepapers, keynote content, technical blogs
  • Ecosystem Development Build strong partnerships across: GPU/XPU vendors System OEMs/ODMs Software stack providers (frameworks, runtimes, orchestration) Influence open ecosystem development while ensuring competitive differentiation Drive interoperability and standardization efforts

Benefits

  • discretionary annual bonus
  • opportunity to receive not only a competitive new hire equity grant, but also annual equity awards
  • Medical, dental and vision plans
  • 401(K) participation including company matching
  • Employee Stock Purchase Program (ESPP)
  • Employee Assistance Program (EAP)
  • company paid holidays
  • paid sick leave
  • vacation time
  • Paid Family Leave and other leaves of absence
© 2024 Teal Labs, Inc
Privacy PolicyTerms of Service