New

GPU AI/ML Power and Performance Attainment Lead

Advanced Micro Devices, Inc.
$152,000.00/Yr.-$228,000.00/Yr.
United States, California, Santa Clara
2485 Augustine Drive (Show on map)
May 13, 2025
WHAT YOU DO AT AMD CHANGES EVERYTHING We care deeply about transforming lives with AMD technology to enrich our industry, our communities, and the world. Our mission is to build great products that accelerate next-generation computing experiences - the building blocks for the data center, artificial intelligence, PCs, gaming and embedded. Underpinning our mission is the AMD culture. We push the limits of innovation to solve the world's most important challenges. We strive for execution excellence while being direct, humble, collaborative, and inclusive of diverse perspectives. AMD together we advance_ THE ROLE: We are seeking an experienced dGPU AI/ML Power and Performance Attainment Lead with expertise or significant interest in GPU power constrained performance. At AMD, our focus is around high-performance gaming (RDNA architecture) and computing (CDNA architecture) using Radeon Technologies, opening new territory and pushing boundaries to gain generation to generation improvements in many performance KPIs not just at SOC but also system level. You will drive discrete CDNA or RDNA dGPU products' power constrained performance achievement methodology advancement and lead execution cross functional teams for performance projection and attainment. This is an exciting domain space to be in working on world-class SOC products. We have a competitive benefit package and an award-wining culture. Join us!. THE PERSON: You have strong communication and presentation skills, strong analytical/problem-solving and project management skills. You are self-directed, a strategic problem solver, able to handle complexity and ambiguity. Finally, you can work effectively and lead through influence in a cross-functional/matrixed organization. Prior pre-silicon power analysis and/or optimization experience using models. A thoughtful leader of industry methodologist in this domain is a big plus. You are highly adept at collaboration among top-thinkers and engineers alike, ready to mentor and guide, and help to elevate the knowledge and skills of the team around you. Adept at collaboration among top-thinkers and senior architects with strong interpersonal skills to work across teams in different geographies. Proven project leadership skills in a matrix organization to drive successful project completion with quality. KEY RESPONSIBILITIES: Advance state of methodology for power constrained performance achievement using power and performance models to scale to all growing GPU product segments with predictability. Work with business unit to define product configurations, capabilities and targets. Profiling and co-optimization of relative performance constrained by power using power and performance models results to forecast and attain to targets throughput development cycles. Track simulation and/or emulation results and correlate with model predictions. Track post silicon performance bring up and debug of new silicon, with and without power constraints and power management features fully enabled. Analyze results and possible causes for underperforming using advanced methodologies. Coordinate corrective actions activity Comprehend the SOC as a complete system which includes HW (Silicon), FW, BIOS & SW and ensure that FW, BIOS & SW are aligned to enable all features, optimizing for performance and power PREFERRED EXPERIENCE: Outstanding foundation in Systems & SoC architecture, with expertise in one or more of the following: CPU or GPU, Memory sub-system, Fabrics, CPU/GPU coherency, Multimedia, I/O subsystems, Clocks, Virtualization Demonstrated expertise in power management microarchitecture, power optimization, along with power impact at architecture, logic design, and circuit levels Advanced working knowledge of power constrained performance analysis and optimization of modern SOCs with CPU/GPU/HW accelerators Excellent knowledge of advanced computer organization/ architecture. Good understanding of model-based performance & power analysis methodologies and practices. Understanding of power/thermal management. Strong analytical and problem-solving skills with a key attention to detail. Data quality analysis such as data mining/machine learning. Experience analyzing CPU, GPU or System-level Micro-Architectural features to identify performance bottlenecks within different workloads is desired Good programming skills: preference for Python language ACADEMIC CREDENTIALS: Undergrad degree required. Bachelor's or Master's degree in related discipline preferred LOCATIONS: Santa Clara CA, Austin TX, Fort Collins CO, Folsom CA #LI-BM1 #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.