Platform Architect, Server Infrastructure

This is a fully remote position, open to applicants in North America.

📋 Description

• Formulate comprehensive thermal architecture strategies for GPU servers, optical interconnects, and CPO-based systems.

• Create system-level methodologies to balance performance, heat dissipation, reliability, and energy efficiency.

• Design and enhance solutions for high-power GPUs and accelerators, dense optical I/O (both pluggable and co-packaged optics), as well as rack- and cluster-level thermal limitations.

• Refine cooling strategies to accommodate high-density AI workloads and scaling of optical bandwidth.

• Evaluate and enhance thermal resistance, junction temperatures, and cooling efficiency.

• Lead the design and assessment of innovative cooling techniques, such as air cooling (high-performance heatsinks, airflow optimization) and liquid cooling (direct-to-chip, cold plates), alongside immersion cooling and other emerging methods.

• Develop thermal solutions for high-speed optical transceivers (400G/800G/1.6T+) and co-packaged optics (CPO) integrated with switch or GPU ASICs.

• Collaborate with silicon photonics teams to co-design thermal-aware optical packaging architectures.

• Design GPU server platforms that are optimized for thermal efficiency, including multi-GPU configurations and interconnect density, power delivery and cooling integration, as well as airflow and liquid loop design.

• Propel advancements in rack-level and data center-level cooling, focusing on high-density rack thermal strategies (50–100kW), integration with facility cooling systems, and optimization for power usage effectiveness (PUE).

⛳️ Requirements

• A Bachelor’s or Master’s degree in Mechanical Engineering, Electrical Engineering, Physics, or a related field is required.

• 8–12+ years of experience in system architecture, thermal engineering, or hardware platform design is necessary.

• Profound expertise in thermal management and cooling technologies for high-performance systems, such as GPU servers, AI/HPC infrastructure, or data center platforms, as well as optical interconnects and high-speed systems (1.6T+).

• Strong comprehension of heat transfer (conduction, convection, liquid cooling systems), power density, and thermal limitations in contemporary computing systems, along with trade-offs between performance, cooling, cost, and reliability.

• Preferred experience in working with hyperscalers or large-scale AI deployments.

• Familiarity with co-packaged optics (CPO) and the thermal challenges associated with silicon photonics.

• Practical design experience with liquid cooling systems and cold plate design, as well as high-density rack and cluster cooling.

• Knowledge of optical module thermal constraints and reliability, as well as data center infrastructure (HVAC, liquid loops, facility integration).

🏝️ Benefits

• Competitive salary and comprehensive benefits package.

• Opportunities for professional development and career growth.

• Collaborative and innovative work environment.

• Flexible work arrangements to promote work-life balance.