Senior Network HW System Engineer

AI Networking Architecture & Platform Development 

• Define and drive networking architectures for MAIA AI training and inference platforms, spanning scale-up and scale-out deployments. Partner across architecture, silicon, firmware, software, and Azure infrastructure teams to deliver networking solutions from concept through datacenter deployment while influencing future networking roadmaps. 

Network Hardware Integration & System Bring-Up 

• Lead the integration, bring-up, and deployment of network hardware technologies including switches, NICs, PHYs, high-speed SerDes interfaces, optics, cables, and backplane solutions. Collaborate with internal teams, ODMs, and technology partners to ensure successful qualification and production readiness. 

AI Fabric Validation, Performance & Reliability 

• Define and execute validation strategies for AI networking infrastructure, including functional, performance, scale, interoperability, reliability, and stress testing. Develop automated qualification frameworks and methodologies to ensure robust operation in rack-scale and cluster-scale AI environments. 

Performance Optimization & Networking Efficiency 

• Analyze and optimize AI fabric performance across distributed training and inference workloads. Evaluate latency, bandwidth utilization, congestion behavior, and collective communication efficiency, translating workload requirements into scalable networking solutions and architecture recommendations. 

High-Speed Interconnect & Emerging Technologies 

• Drive qualification and deployment of next-generation networking technologies, including high-speed copper and optical interconnects, PAM4-based SerDes, advanced optics, and future networking innovations such as LPO, LRO, CPO, and silicon photonics. Evaluate technology tradeoffs across performance, power, reliability, and scalability. 

Debug, Telemetry & Automation 

• Lead root-cause analysis of networking and AI fabric issues spanning physical layer, network protocols, and distributed AI communication layers. Develop telemetry, diagnostics, automation, and fleet monitoring solutions that improve network reliability, accelerate issue resolution, and enhance engineering productivity. 

Key Responsibilities 

• Drive end-to-end architecture, integration, validation, and deployment of networking infrastructure for MAIA AI systems across scale-up and scale-out environments. 

• Partner with silicon, firmware, software, hardware, and Azure infrastructure teams to define networking requirements and deliver scalable, reliable, and high-performance AI fabrics. 

• Lead bring-up, qualification, and optimization of network subsystems including switches, NICs, PHYs, optics, cables, and high-speed SerDes technologies. 

• Develop validation and performance methodologies for AI networking infrastructure, ensuring readiness across functionality, scale, reliability, and stress conditions. 

• Drive root-cause analysis, telemetry, and automation solutions to improve network resiliency, operational efficiency, and fleet health. 

• Evaluate and influence next-generation networking technologies and architectures required to support future AI workloads and hyperscale deployments. 

Preferred Qualifications 

AI Infrastructure Experience 

• Experience developing GPU, FPGA, TPU, AI accelerator, or HPC-based systems. 

• Familiarity with AI workload communication patterns and collective operations. 

• Understanding of large-scale distributed AI training environments. 

Optical & Interconnect Expertise 

Deep knowledge of: 

• Optical transceivers (DR4, DR8, FR4) 

• DSP architectures 

• TIAs and drivers 

• Optical link budgets 

• OMA, TDECQ, receiver sensitivity analysis 

• Silicon photonics technologies 

• Co-packaged optics architectures 

Industry Standards 

Experience with: 

• IEEE Ethernet standards 

• OIF specifications 

• CMIS management frameworks 

• Ultra Ethernet Consortium technologies 

• Future 224G and 448G ecosystems 

Datacenter & Manufacturing 

• Experience with hyperscale datacenter deployments. 

• Knowledge of ODM, CM, and supplier ecosystems. 

• Experience managing products through EVT, DVT, PVT, and production ramps. 

Software & Automation 

• Experience with Linux environments and automation frameworks. 

• Background developing telemetry, diagnostics, validation, and qualification tooling. 

• Familiarity with scripting and data analysis environments.