AI Systems Performance Engineer
About the 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.
As a member of AMD's AI Systems Power and Performance Engineering team, you will play a critical role in evaluating and optimizing the performance of next-generation AI workloads on AMD embedded and client platforms. Working at the intersection of AI software, hardware architecture, and system performance, you will help deliver data-driven insights that influence product development, competitive positioning, and customer success. You will collaborate with AI software teams, architects, firmware developers, platform engineers, product planners, and business stakeholders to characterize AI workloads, identify performance bottlenecks, and drive continuous improvements across AMD's AI-enabled products.
The ideal candidate is passionate about AI technologies and system performance. You enjoy understanding how modern AI workloads interact with hardware and software systems and are naturally curious when investigating performance anomalies. You are comfortable working in Linux environments, analyzing workload behavior, and leveraging profiling tools to understand system-level bottlenecks. You thrive in collaborative environments and enjoy translating complex technical findings into actionable insights for engineering teams.
Responsibilities
- Benchmark and characterize AI inference workloads across AMD embedded and client platforms.
- Execute performance, power, and efficiency analysis of modern AI workloads, including Large Language Models (LLMs), Vision Language Models (V