About this role
ADVANCE YOUR CAREER. ADVANCE THE WORLD.
At AMD, we believe technology has the power to solve the world’s most important challenges. From advancing healthcare and scientific discovery to powering AI and the technologies people rely on every day, innovation at AMD is shaping the future.
Whether you’re designing next-gen processors, enabling AI breakthroughs, or bringing leading edge products to market, every role at AMD contributes to something bigger — technology that moves the world forward. Join us and, together, we’ll advance your career.
THE ROLE:
AMD's Data Center GPU (DCGPU) products power the world's most demanding AI and high-performance computing workloads. The Diagnostics team builds the test software that proves these products work, from pre-silicon emulation through first silicon, bring-up, new product introduction (NPI) and high-volume manufacturing.
As the Diagnostics Technical Lead, you will own the technical direction of the diagnostics solution for one or more DCGPU programs. A key focus of the role is system-level test coverage for the AMD Instinct Helios rack level solution. This includes the compute tray to the full rack, including the Helios rack-scale platform, delivered through ROCm-based diagnostics. You will define what must be tested, how it will be tested, and you will make sure the diagnostics suite delivers the coverage, quality and test time the product needs. This is a hands-on technical leadership role with global scope: you will set strategy, guide engineers across sites, and be the technical voice of Diagnostics with silicon, platform, software, rack integration and manufacturing partners.
THE PERSON:
You combine strong software design skills with a deep understanding of Instinct SoC hardware and System platform. The successful candidate needs to be AI savvy and use AI for efficiency improvements. You are comfortable moving between architecture discussions, C++ code and a failing board on the bench. You communicate clearly with both software developers and silicon design teams, and you can explain complex technical trade-offs to program managers and leadership. You lead through influence, set a high bar for quality, and thrive in a fast-paced, results-driven environment.
KEY RESPONSIBILITIES:
Technical leadership and strategy
- Own the end-to-end diagnostics solution for DCGPU programs, including its quality, test coverage and completeness.
- Define and communicate diagnostics goals, strategy, risks and key requirements to program managers, engineering managers, IP validation architects and framework architects.
- Drive the technical requirements needed to reach feature coverage and hardware bug capture targets, and track progress against them.
- Mentor engineers and review designs and code to raise the technical bar across the team.
Pre-silicon and verification
- Own the diagnostics pre-silicon emulation strategy across software-based and FPGA-based emulation models.
- Define RTL coverage requirements before tape-out, the diagnostics verification strategy and readiness criteria before silicon arrives.
- Own the SoC system-level feature verification methodology and plan.
Silicon bring-up and cross-functional execution
- Lead diagnostics through SoC bring-up, feature enablement and performance profiling.
- Partner with Platform Validation, ROCm software, hardware architecture and other stakeholders to meet key program milestones with the agreed coverage metrics.
- Lead system-level debug of complex hardware and software issues to root cause.
System-level test coverage: MI450 tray, rack and Helios
- Own the system-level diagnostics strategy and coverage plan for AMD Instinct series, ranging from the single GPU and compute tray to the Helios rack-scale solution.
- Define test coverage for the scale-up fabric (UALink over Ethernet) and scale-out networking (Ultra Ethernet with AMD AI NICs), including link training, bandwidth, latency, error injection and fault isolation.
- Develop ROCm-based diagnostics and stress workloads for Compute, HBM, interconnect that prove tray and rack health at scale.
- Define rack-level burn-in, health-check and fault-isolation flows, RMA isolation, review coverage gaps/learnings and define test-time targets for manufacturing.
Production and customer quality
- Work with Product Engineering to deliver high-quality products to customers: debug defects and improve yield, coverage and test time during NPI and volume production.
- Provide diagnostics support to contract manufacturers and board engineering teams.
PREFERRED EXPERIENCE
- Champions AI-driven engineering, applying machine learning and AI agents to test coverage and failure analysis, and automated root-cause analysis.
- Experience in software development, silicon validation or diagnostics, including technical leadership of a team or program.
- Proven experience with IP and SoC verification, working closely with hardware designers.
- Strong understanding of SoC architecture, including CPU, compute GPU, system interconnects, memory/HBM and security blocks, and the ability to identify the critical areas for verification focus.
- Strong system level experience with multi-GPU servers, AI/HPC platforms or rack scale infrastructure.
- Hands-on experience across assembled GPU board (L6), compute tray/node (L10) and full rack (L11) owning diagnostics content, bring-up, and fault isolation for integrated hardware.
- Track record debugging failures that reproduce only in an assembled system such as power sequencing, thermal and liquid-cooling interaction, link training across connectors and cables, cross-GPU fabric faults, isolating them to the correct FRU for rework or RMA.
- Experience defining test content, coverage and test-time targets for L6–L11 manufacturing flows in partnership with contract manufacturers.
- Experience with C/C++ for verifying complex IP blocks and system-level features.
- Hands-on experience with SoC bring-up and strong system-level debug skills.
- Proficient with Linux and source control systems such as Git and Perforce.
- Hands-on experience with system-level test (SLT) and diagnostics for multi-GPU servers or rack-scale systems, including defining test coverage and tracking test escapes.
- Working knowledge of GPU interconnects and data center networking (PCIe, AMD Infinity Fabric, Ethernet/RDMA) and debugging link and fabric failures at node and rack scale.
- Experience developing GPU diagnostics or stress tests on ROCm or a comparable GPU software stack
- Experience developing machine learning, HPC or general-purpose GPU compute applications.
- Device driver or low-level firmware development experience.
- Experience with pre-silicon emulation and FPGA prototyping platforms.
- Knowledge of manufacturing test, including ATE, wafer sort and system-level test (SLT).
- Experience working across geographically distributed teams.
- Knowledge of rack-scale infrastructure, including OCP Open Rack, liquid cooling, power shelves, BMC/Redfish and out-of-band management.
ACADEMIC CREDENTIALS:
- Bachelor's or Master's degree in Computer Science, Computer Engineering, Electrical Engineering or a related field.
LOCATION:
Markham, ON
#LI-AJ1
Benefits offered are described: AMD benefits at a glance .
AMD does not accept unsolicited resumes from headhunters, recruitment agencies, or fee-based recruitment services. AMD and its subsidiaries are equal opportunity, inclusive employers and will consider all applicants without regard to age, ancestry, color, marital status, medical condition, mental or physical disability, national origin, race, religion, political and/or third-party affiliation, sex, pregnancy, sexual orientation, gender identity, military or veteran status, or any other characteristic protected by law. We encourage applications from all qualified candidates and will accommodate applicants’ needs under the respective laws throughout all stages of the recruitment and selection process.
AMD may use Artificial Intelligence to help screen, assess or select applicants for this position. AMD’s “Responsible AI Policy” is available here.
This posting is for an existing vacancy.