Principal Engineer, Hardware Design - Networking

Summary

Celestica is seeking a Principal Hardware Systems Architect for Networking Platforms to provide senior technical leadership for the architecture and development of next-generation AI, cloud, and high-performance data center networking platforms.

This role will lead networking-platform architecture spanning high-performance Ethernet and InfiniBand-class fabrics, switching systems, NICs/DPUs, high-speed SerDes, optical and electrical interconnects, and scale-out network architectures, while collaborating with peer domain architects and engineering leaders to define complete rack and multi-rack systems incorporating compute, power, thermal, mechanical, firmware, and system-management technologies.

This is a system and platform architecture role, not an ASIC/chip-design role or enterprise IT/network-operations role. The successful candidate will operate above the component level, translating customer requirements, technology roadmaps, and AI workload needs into scalable networking-platform architectures.

A critical aspect of the position is understanding that next-generation AI networking cannot be optimized independently from compute. The Network Architect will partner closely with Celestica’s Compute Architect and other domain experts to optimize the complete AI system from compute connectivity through rack and multi-rack network fabrics.

Skills & Responsibilities:

Networking Platform Architecture

• Define architecture for next-generation AI, cloud, hyperscale, and high-performance data center networking platforms.
• Own architectural definition of:

  • Ethernet and InfiniBand-class networking

  • Switch architectures

  • Switching silicon/NPU integration

  • NIC, SmartNIC, SuperNIC, and DPU architectures

  • High-speed SerDes

  • Optical and electrical interconnects

  • Scale-out network fabrics

  • Network topology

  • Inter-rack connectivity

• Establish networking-system requirements, interfaces, partitioning, and architectural tradeoffs.
• Evaluate alternatives based on bandwidth, latency, congestion, power, thermal density, reliability, cost, scalability, serviceability, and manufacturability.
• Develop reusable networking-platform architectures and building blocks that can be leveraged across customers and programs.
• Lead early architecture studies, feasibility assessments, proof-of-concept development, and platform definition.

Experience Requirements

• BS or MS in Electrical, Computer Engineering, Computer Science, Physics, or a related field.
• Typically 12+ years in hardware development with strong focus on networking, switching, AI, or cloud platforms.
• Proven experience defining system architecture for complex networking platforms.
• Deep knowledge of Ethernet/InfiniBand, switch architectures, NICs/DPUs, PCIe, SerDes, and optical/electrical interconnects.
• Strong understanding of switching NPUs/ASICs, CPUs, accelerators, PCIe/CXL, and system integration.
• Solid grasp of networking, compute, power, thermal, and mechanical architecture interplay.
• Track record of taking complex platforms from early architecture to production.
• Ability to evaluate tradeoffs across bandwidth, latency, cost, power, thermal, reliability, and schedule.
• Excellent technical communication and presentation skills.
• Proven ability to influence cross-functional technical teams without direct authority.
• Direct experience engaging with customers, silicon vendors, and partners.

Typical Education & Preferred Qualifications

• Bachelor’s or Master’s degree in Electrical Engineering, Computer Engineering, Computer Science, Physics, or related technical field.  Educational Requirements may vary by geography
• Architecting networking systems for large-scale AI training or inference clusters.
• High-performance Ethernet or InfiniBand architectures.
• Modern switching silicon, NIC, SmartNIC, SuperNIC, or DPU technologies.
• 800G, 1.6T, and next-generation high-speed networking.
• Advanced optics and evolving electrical/optical interconnect architectures.
• GPU scale-up fabrics and accelerator interconnect architectures.
• Rack-scale and multi-rack AI infrastructure.
• High-power, liquid-cooled networking or compute systems.
• Collaboration with hyperscale or cloud service provider customers.
• Developing reusable platform architectures.
• Contributing to roadmaps, standards, patents, or advanced development.

Notes

This job description is not intended to be an exhaustive list of all duties and responsibilities of the position. Employees are held accountable for all duties of the job. Job duties and the % of time identified for any function are subject to change at any time.