Santa Clara, CA30+ days ago
What we need to see: To be successful in this role, you should have: • Bachelors, Masters, PhD, or equivalent experience in relevant fields (Computer Engineering, Computer Science, Electrical Engineering, AI) • 8+ years of experience in CPU or GPU performance, working on microarchitecture bottleneck analysis • Demonstrated expertise in conducting hardware power and performance analysis with an understanding of microarchitecture design trade-offs • Experience characterizing and optimizing AI, gaming and/or cloud workloads, including software and compiler-level optimizations • Strong programming skills in C, C++, Python, and scripting languages, with hands-on experience configuring, deploying, and running AI models • Good understanding of performance analysis methodologies, including code instrumentation, sampling, and roofline analysis • Demonstrated problem-solving skills with a desire to explore new areas, identify gaps, and think creatively to develop solutions • Ability to analyze complex data, draw insightful conclusions, and form hypotheses to explain findings • Strong presentation skills, with the ability to communicate complex ideas and data concisely to various audiences. What youll be doing: • Architect next-generation cloud infrastructure optimized for AI workloads alongside gaming • Perform deep performance and power analysis of GPU/CPU microarchitecture features for AI inference and gaming workloads • Deploy, optimize, and benchmark AI/gaming kernels in the cloud across various system configurations • Build models and tools to guide platform decisions balancing performance, power, and cost • Present findings to cross-functional teams including product, engineering, and executives • Collaborate with a team of highly skilled engineers, architects, and researchers, working together to successfully implement world-class solutions.