Datacenter Post-Silicon Performance Architect

Advanced Micro Devices • Santa Clara, CA

80d • 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. At AMD, we focus on providing the highest performance computing products to the industry's leading enterprise and cloud providers. In the AMD Server Performance Group, we build on our depth in microarchitecture knowledge and simulation to analyze and optimize high-performance System-on-a-Chip (SoC) designs for critical areas such as cloud computing, AI, and high-performance computing. We work closely with our partners to ensure that we provide the best performance solutions for their applications and cloud computing offerings. We also work closely with the silicon design teams to influence next generation server compute products. Typical roles include performance analysis of the hardware microarchitecture and software stack as well as performance model development. As a senior member of the technical team, you'll be leading projects that are critical to AMD's server business segment. Candidates seeking the most sophisticated and exciting challenges in the computing industry are encouraged to apply. We are passionate about performance innovation. Check out our opportunity. We have a competitive benefits package and an award-winning culture. Join us!

Requirements

• Experience with multi-core systems and multi-thread interactions
• Experience with CPU, GPU, or computer system microarchitecture (ideally familiarity with all three)
• Experience with the development and usage of computer system performance models
• Experience with datacenter and AI workload analysis
• Proficiency in principles and methods of microarchitecture, software, and hardware relevant to performance engineering
• Experience in IO subsystem microarchitecture performance modeling and strong background in PCI-E/CXL microarchitecture and protocols

Responsibilities

• Collaborate with performance experts from our key partner companies to resolve performance issues and optimize the performance and TCO of their AMD datacenter technologies.
• Collect and analyze performance profiling data and traces from customer deployments of AMD based servers and share the insights to drive features into the next generation of datacenter CPU and GPU hardware designs.
• Responsible for analyzing and optimizing workloads running on AMD based hardware in the cloud computing environments of our key partners. This analysis spans the full stack including the application and related frameworks, the Java Virtual Machine, operating system (Linux and Windows Server), hypervisor, network and storage drivers, BIOS, CPU core, memory & I/O subsystems.
• Responsible for exploring opportunities to improve server performance through hardware & software co-optimization.
• Debug performance issues and identify software stack specific issues and prototype solutions to fix them.
• Micro-benchmarking, analyzing and tracing various benchmarks, workload characterization, competitive analysis on various hardware platforms, identifying bottlenecks and proposing feedback and solutions for performance improvement.
• Work closely with other team members to understand design architecture and to propose solutions to improve/enhance performance with given SoC/IP and markets.

What This Job Offers

• Industry: Computer and Electronic Product Manufacturing
• Education Level: Bachelor's degree
• Number of Employees: 5,001-10,000 employees