Principal Server Platform Engineer (CPU/GPU Systems)
ZT Systems
Secaucus, NJ
Full Time
Lead Level
12+ years
Posted 3 weeks ago
Interested in this position?
Upload your resume and we'll match you with this and other relevant opportunities.
Upload Your ResumeAbout This Role
This role is responsible for the end-to-end platform design of CPU and GPU-based server systems for AI, machine learning, and cloud compute workloads. It involves bridging system architecture, hardware design, validation, and manufacturing.
Responsibilities
- Define and own server platform architectures incorporating CPUs, GPUs, memory, and IO subsystems
- Drive platform-level specifications, design guides, and architectural decisions
- Lead system integration and validation across baseboards, accelerator cards, and interconnect fabrics
- Partner with silicon vendors and internal teams to ensure optimal platform performance and reliability
- Lead bring-up and debug of complex multiprocessor and GPU-accelerated systems
- Specify production test strategies and validation coverage
- Drive cost, performance, power, and reliability trade-offs at the platform level
- Mentor engineers and provide technical direction across multiple programs
Requirements
- 12+ years of experience working on server or compute platforms
- Strong knowledge of x86 or ARM-based systems and GPU accelerators
- Experience with PCIe fabrics, memory subsystems, and high-speed IO
- Familiarity with system validation, silicon bring-up, and platform debug
Qualifications
- Bachelor’s degree in Electrical Engineering, Computer Engineering, or equivalent experience
- 12+ years of experience working on server or compute platforms
Skills
AI
*
Machine Learning
*
Written communication
*
Verbal communication
*
ARM
*
x86
*
CPU systems
*
GPU systems
*
Cloud compute
*
PCIe fabrics
*
Memory subsystems
*
High-speed IO
*
System validation
*
Silicon bring-up
*
Platform debug
*
Influence architecture and design decisions
*
* Required skills