AI Scale-up Switch System Design Engineer

Advanced Micro Devices, Inc•Secaucus, NJ

About The Position

We are looking for a hands-on, technically sharp system design engineer to join our growing team and lead the bring-up of cutting-edge scale-up switches at the heart of next-generation AI rack infrastructure. As a key contributor, you will bring deep expertise in high-speed Ethernet, server management, and platform validation to drive switch platforms from initial power-on through full system qualification. In this role, you will take full ownership of bring-up execution, apply your debugging skills to solve complex multi-layer problems, and collaborate closely with hardware, firmware, and software teams to deliver production-ready systems.

Requirements

Extensive hands-on experience in hardware bring-up, platform validation, or high-speed networking silicon characterization
Experience with high-speed switch ASICs (Broadcom TH6/Tomahawk series preferred) and familiarity with Broadcom's SDK/DAPI frameworks
Deep understanding of high-speed Ethernet standards (400GbE, 800GbE) including AN/LT (IEEE 802.3), RS-FEC / KP4-FEC, and PAM4 SerDes technology
Hands-on experience with PRBS testing, BER measurement, eye diagram analysis, and Snake/loopback traffic validation methodologies
Familiarity with LinkCAT or equivalent PHY/link characterization tools
Experience with server management protocols: IPMI, Redfish/OpenBMC, KCS, IPMB, and PLDM for out-of-band control and telemetry
Proficiency in Python for test automation, log parsing, and data analysis
Strong debugging skills — comfortable working across hardware (oscilloscope, protocol analyzer), firmware logs, and software traces to isolate root cause
Experience reading schematics and PCB layout to correlate signal integrity observations with hardware design
Excellent communication skills with the ability to document findings clearly and collaborate across multidisciplinary teams
Bachelor’s/Master’s degree in Computer Science or related field strongly preferred

Nice To Haves

Experience with high-density switch/router platforms or AI/ML fabric infrastructure is a strong plus

Responsibilities

Lead the system bring-up and validation of state-of-the-art AI scale-up switches purpose-built for high-density GPU compute racks, from initial power-on through full system validation
Perform high-speed SerDes and link bring-up, including configuring and validating Auto-Negotiation/Link Training (AN/LT), tuning TX equalization, and characterizing signal integrity across 200G/400G/800G interfaces
Execute comprehensive link qualification testing using PRBS (Pseudo-Random Binary Sequence), Snake Traffic loopback testing, and FEC (Forward Error Correction) analysis to validate BER performance at scale
Utilize LinkCAT and Broadcom SDK tools to characterize port performance, diagnose link failures, and validate PHY configurations across large port counts
Integrate and validate server management infrastructure including BMC/IPMI, Redfish API, and out-of-band management workflows for automated bring-up and health monitoring
Develop and maintain bring-up scripts and test automation (Python) to accelerate validation coverage across chassis configurations
Debug complex system-level failures spanning hardware, firmware, and software including signal integrity issues, firmware crashes, and management plane anomalies and drive issues to root cause
Collaborate with hardware, firmware, and software teams to reproduce failures, document findings, and verify fixes across platform revisions
Maintain detailed bring-up documentation, test reports, and issue tracking throughout the product development lifecycle