Neo Cloud - Principal Hardware Systems Engineer

Neo Cloud is a next-generation AI neocloud building and operating AI infrastructure for demanding workloads. The Principal Hardware Systems Engineer will design, deploy, operate, and architect large-scale AI hardware systems while translating customer and workload requirements into secure, resilient, and cost-effective solutions. The role also provides technical leadership, mentorship, and direction for the hardware organization.

Responsibilities:

• Identifying customer requirements
• Engage directly with customers, solutions architects, and product teams to understand future hardware requirements for AI/ML workloads
• Extrapolate from current usage patterns and industry trends to anticipate future requirements
• Partner with vendors and drive their roadmaps
• Design, implement, and operate AI cloud hardware
• Architect, evaluate, and Deploy NVIDIA GPU infrastructure, including Blackwell-based B200, GB200, GB300, DGX and NVL rack-scale systems
• Design rack-scale infrastructure encompassing NVLink and NVSwitch fabrics, Infiniband or Spectrum-X Ethernet with RoCE for scale-out networking; power delivery, liquid cooling, cabling and serviceability
• Take a system-level approach that accounts for the full characteristics of AI workloads, building end-to-end solutions
• Architect for the specific demands of AI workloads focusing on performance, security, resiliency and cost
• Design and implement consistent and efficient hardware operation
• Take end-to-end ownership of hardware from design, supply chain planning, deployment, operation and ultimately deprecation
• Ensure security and compliance
• Strong debugging skills and analytical skills to identify failures across a variety of electrical, thermal, optical, mechanical and software failures
• Strong bias to action and resolution of technical decisions
• Set technical direction and best practices for the hardware organization; author and review design documents for significant architectural changes
• Provide deep technical mentorship to senior and staff engineers; raise the engineering bar across the team through code review, design review, and hands-on collaboration
• Influence technical strategy across adjacent teams

Requirements:

• 10+ years of professional hardware engineering experience building and operating hardware at massive scale
• Direct experience with AI-focused hardware deployments across different hardware vendors, including NVIDIA GPU platforms
• Experience with NVIDIA BLackwell, GB200 or GB300 NVL72
• Experience with NVLink, NVSwitch, InfiniBand or Spectrum-X Ethernet, ConnectX networking, and BlueField DPUs
• Deep system level expertise
• Proven experience operating large-scale distributed systems in production, including on-call ownership, incident response, and driving systemic reliability improvements
• Strong systems programming skills
• Excellent written and verbal communication skills