Senior GPU Performance and Power Benchmark Engineer

WHAT YOU DO AT AMD CHANGES EVERYTHING

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 ROLE:

AMD is committed to contributing to the future of the computing ecosystem, such as by participating in the development of industry standard performance and power benchmarks. This individual will join AMD's Data Center Solutions Group (DSG) Architecture and Strategy team, a highly experienced organization of hardware and software engineers driving innovation across the full server stack-from node-level and rack-level design to security, cloud computing, memory technologies, high-performance fabrics, and beyond. In this role, the candidate will lead AMD's involvement in shaping the next generation of industry standard GPU performance and power benchmarks. These benchmarks are expected to play a significant role in government energy-efficiency regulations worldwide and will help inform how the efficiency of GPU-based servers is evaluated, positioned, and communicated across the industry.

THE PERSON:

• A self-starter that possesses excellent communication, leadership and interpersonal skills to be able to interact both inside and outside of AMD.
• Can overcome complex hurdles with minimal support, while keeping management appropriately informed and escalating important decisions when warranted.
• Be well-spoken with strong leadership, debate and influencing skills, especially in peer groups
• Have excellent problem-solving skills, an inquisitive mindset, and a strong focus on automation and technical investigation.

KEY RESPONSIBILITIES:

• Represent AMD externally to industry standard benchmark development organizations, including attending remote and in person meetings
• Lead AMD strategy for the development and measurement of a series of industry standard GPU performance and power benchmarks
• Measure performance and power on AMD and competitive GPU servers, including collection of relevant telemetry data, such as hardware performance counters.
• Investigate and root cause performance or power anomalies related to in development benchmarks, with support from relevant experts
• Develop and present benchmark design or adjustment proposals
• Internally coordinate with and inform GPU software and hardware architecture, product management and marketing teams

PREFERRED EXPERIENCE:

• Strong knowledge of Artificial Intelligence (AI) and machine learning concepts, with practical experience applying these techniques to solve real-world problems through research or industry work.
• Deep technical understanding of server GPU hardware and software architecture, along with solid knowledge of server system and CPU architecture, including GPU/AI accelerator hardware-software interactions.
• Experience with GPU programming platforms like CUDA or HIP and deep learning frameworks, such as PyTorch, Triton, or JAX.
• Strong programming and scripting skills in languages such as Python, C++ and Java and using tools like Git.
• Understanding of multi-GPU communication technologies, such as UALink, NVLink, RCCL, and NCCL topologies and their performance characteristics.
• Advanced Linux OS and system expertise, including containers (e.g. Docker), system bring-up, debugging, and configuration, as well as familiarity with Windows.
• Experience with power and performance benchmarking, including experience with CPU performance counters, workload profiling and software profiling/debugging tools.
• Advanced data analysis skills, especially in support of performance characterization, benchmarking, and optimization.
• Experience with industry standards organization, especially benchmark development organizations, such as SPEC, MLCommons, or TPC, a strong plus.

ACADEMIC CREDENTIALS:

• Bachelor's or higher degree in Electrical or Computer Engineering

LOCATION:

• Austin, TX (team-based), with flexibility for other locations depending on candidate experience.

This role is not eligible for visa sponsorship.

#LI-EV1

#LI-HYBRID

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.