Senior Principal Platform Architect

Job Title

Senior Principal Platform Architect

Role Summary

Lead system-level architecture for UALink scale-up network chassis, defining end-to-end hardware, firmware, and management interfaces that enable multi-ASIC switch platforms in hyperscale AI data centers. You will drive chassis topology, power and cooling orchestration, platform management (BMC/OpenBMC/Redfish), and cross-domain integration between silicon, board-level hardware, and cloud orchestration.

Work cross-functionally with silicon, electrical, mechanical, firmware, and software teams to deliver a production-ready platform for hyperscale customers. Renesas is a global semiconductor company with ~21,000 employees focused on automotive, industrial, infrastructure and IoT solutions.

Experience Level

Senior — 20+ years of architectural experience in high-performance server platforms, hyperscale network switches, or data center infrastructure.

Responsibilities

Primary responsibilities include system architecture, platform management design, and ensuring reliability and serviceability at rack and datacenter scale.

• Define chassis, backplane and rack-scale topologies for UALink scale-up switches; specify high-speed interconnect routing and cabling architectures.
• Collaborate with SI/PI and electrical teams to specify SerDes routing, signal/power integrity targets, and BER objectives across PCBs, flyovers, and optics.
• Architect rack- and row-level fabrics to optimize collective communication patterns for large GPU clusters.
• Design the platform management plane: BMC/OpenBMC architecture, Redfish-based management, PLDM over MCTP, and provisioning workflows.
• Define boot, multi-rail power sequencing, firmware update orchestration, and secure initialization flows for multi-node systems.
• Develop platform-level security requirements including firmware resiliency (NIST SP 800-193), SPDM component attestation, and secure enclave integration.
• Specify platform RAS strategies: fault isolation, link rerouting, and hot-swap behaviors to maintain AI training clusters.
• Establish thermal and power orchestration frameworks to manage transient AI power draws with liquid/air cooling and high-density power delivery.
• Lead cross-disciplinary teams and represent the platform in standards and customer engagements.

Requirements

Must-have technical skills and experience to perform the role.

• Deep expertise in system-level interconnects and high-speed fabrics (UALink, NVLink, PCIe Gen‑6/7, CXL, Ultra Ethernet).
• Proven experience with platform management standards and implementations: OpenBMC, Redfish, IPMI, MCTP, PLDM, SPDM.
• Strong understanding of firmware/boot/initialization frameworks (UEFI, ACPI) and kernel/driver interactions.
• Experience with datacenter rack architectures, liquid cooling, and high-density 48V/54V power delivery at scale.
• Demonstrated ability to architect RAS, thermal/power control, and telemetry for large-scale systems.
• Excellent cross-functional leadership and communication skills; experience engaging hyperscale cloud customers and suppliers.

Nice-to-have:

• Track record of delivering multi-million-gate switching or compute platforms into hyperscale providers (AWS, Azure, GCP, Meta).
• Active participation or leadership in standards bodies (UALink Consortium, Ultra Ethernet Consortium, OCP).
• Experience with ultra-high-density accelerator form factors (e.g., modern Nvidia or AMD accelerator grids).

Education Requirements

Master's or Ph.D. in Electrical Engineering, Computer Engineering, Computer Science, or a related field (specified in the posting).

About the Company

Company: Renesas

Headquarters: Hitachinaka, Japan

Renesas is a global leader in embedded semiconductor solutions, providing high-quality products across automotive, industrial, infrastructure, and IoT sectors. With over 22,000 employees in more than 30 countries, the company focuses on scalable solutions that enhance user experience and drive innovation while committed to sustainability and energy efficiency.