Senior GPU Network Software Architect (C/C++)

Advanced Micro Devices, Inc.; Santa Clara, Northern (CA, KY); Hybrid; USD 230,000 - 320,000; Full time

Job summary

Advanced Micro Devices, Inc. (AMD) is seeking a Principal Member of Technical Staff to lead end‑to‑end delivery of scale‑up networking and GPU software for Instinct GPUs. You will own architecture, bring‑up and optimization across scale‑up fabrics, firmware, drivers and ROCm software, partnering with silicon, hardware and cloud teams.

You will guide cross‑layer debugging, establish performance goals and steer multi‑team execution to production readiness in rack‑scale AI systems.

Qualifications

• Experience in system software development for GPUs, accelerators, NICs or switches.
• Strong Linux kernel and driver development background.
• Proven ability to lead cross‑functional teams and drive complex hardware/software bring‑ups.
• Proficiency in C/C++ and Python; Go or Rust a plus.

Responsibilities

• Define software architecture for scale‑up switch fabrics and ROCm stack integration.
• Lead integration of switch software (SONiC, SAI, SDKs) and firmware bring‑up for GPUs.
• Architect and develop GPU firmware components and system management workflows.
• Lead Linux kernel driver development for Instinct GPUs (amdgpu/KFD).
• Drive performance, reliability and scalability goals for multi‑GPU workloads.
• Mentor engineers and coordinate execution across distributed teams.

Skills

System software

GPU software

Linux kernel

C/C++

Python

Go

Rust

JTAG debugging

ROCm

Leadership

Education

Bachelor's or Master’s degree in Computer Science/Engineering

Tools

Broadcom SDK

SAI

SONiC

Redfish

PLDM

Job description

Advanced Micro Devices, Inc. (AMD) is seeking a Principal Member of Technical Staff to lead end‑to‑end delivery of scale‑up networking and GPU software for Instinct GPUs. You will own architecture, bring‑up and optimization across scale‑up fabrics, firmware, drivers and ROCm software, partnering with silicon, hardware and cloud teams.

You will guide cross‑layer debugging, establish performance goals and steer multi‑team execution to production readiness in rack‑scale AI systems.