Principal AI Systems Engineer – GPU Reliability & Customer Debug

Advanced Micro Devices, Inc

6h•Hybrid

About The Position

At AMD, our mission is to build great products that accelerate next-generation computing experiences—from AI and data centers, to PCs, gaming and embedded systems. Grounded in a culture of innovation and collaboration, we believe real progress comes from bold ideas, human ingenuity and a shared passion to create something extraordinary. When you join AMD, you’ll discover the real differentiator is our culture. We push the limits of innovation to solve the world’s most important challenges—striving for execution excellence, while being direct, humble, collaborative, and inclusive of diverse perspectives. Join us as we shape the future of AI and beyond. Together, we advance your career. The AI Customer Engineering organization is looking for a Principal AI Systems Engineer to help customers achieve best‑in‑class telemetry capabilities on AMD GPU platforms. This is a hands‑on, customer‑facing role leading full-stack debug of AI infrastructure focusing on Reliability, Availability, and Serviceability (RAS) features. THE PERSON: Ideal candidate would be a senior technologist who has significant experience in server architecture, RAS, debug with firmware and software skillset. Expert in Data Center and AI domains with good understanding of AI workload optimization by resolving customer design issues. Experience in working with different owners of the functional code stack as well as the ability to drive issues to resolutions with innovative solutions. Experience in debugging of complex full stack SW/FW/HW issues is a must, understand the flow of a GPU through different layers of a system and be able to validate the items connecting to the GPU SOC (PCIe, VR’s, RMs, retimers, HBM, internal networking). Communication is essential in working with different owners of the functional code stack as well as the ability to drive issues via phone calls, chat messages, e-mails. Hands on experience with Hardware in a Data Center environment will be required.

Requirements

Significant experience in SoC architecture, RAS debug of complex system level issues
Strong debug capabilities of SoC platforms including Server CPU/GPU/FPGA in single and multi-node clusters
Solid experience in Server CPU/GPU microcode, DMTF specs, BMC firmware, memory and PCIe protocols
Proven experience in accelerator software workflows including RAS, Security, power and performance
Hands-on troubleshooting experience in solving technical issues; own the problem and drive for resolution
Hands-on experience in using industry debug tools, scopes as well examine board level power integrity
Good balance of understanding with hardware, architecture, and software expertise
Solid programming skills in Python, C, or C++

Nice To Haves

Demonstrable experience in facilitating Agile, Scrum or Kanban
Skilled in scripting languages such as Perl, Ruby, and Shell script
Experience running, analyzing, and system benchmarks
Proficient with revision control (GIT, SVN and CVS)
Experience crafting and supporting cloud environments, including IaaS and PaaS
Proven ability to drive resolution of critical problems within a lab, Datacenter
Relationship with external customers/partners and able to help resolve problems in their Data Center

Responsibilities

Drive resolutions for customer issues using internal debug tools with a goal to root cause and validate the fix
Provide technical leadership to the cross functional debug team driving to root cause issues
Ability to setup hardware systems and probe components of a board; check electrical and power signals and validate a system using different AI workloads
Communicate / Document flows and methods of bring-up, boot-up, system initialization and debug
Lead technical presentations demonstrating a good understanding of application, data, infrastructure, architecture expertise and application systems design
Collaborate with application, and infrastructure architects and be responsible for the defining-designing-delivering of the technical architecture, patterns, technical quality, risks, fitness for purpose and operability of technical architecture solutions
Be a leader and mentor to the operation team; be hands-on and lead by example
Able to proactively support team culture that fosters knowledge sharing, excellence, and collaboration