Technical Intern, CPU Architecture

Summary: Ampere is a semiconductor design company focused on high-performance, energy efficient AI compute. The Technical Intern in CPU Architecture will participate in architectural definition and performance analysis of new systems tailored for modern workloads, while gaining exposure to the company's operations and contributing to impactful projects. Responsibilities: - Learning the CPU performance model from senior team members and helping to develop, deploy, and run microarchitecture studies for future products - Working with microarchitecture designers in performing studies on current and future generation of CPUs - Driving performance correlation of models using post-silicon measurement data or pre-silicon simulation results - Collecting silicon performance measurements and understanding how to vet data and filter anomalous results - Developing automated performance testing and data post-processing - Developing visualization tools to assist in performance analysis - Running micro-benchmarks and creating supporting models/relationships using the collected data - Developing spreadsheet macros to further prepare/present performance data in appropriate formats - Investigating performance anomalies with help from senior performance architects - Developing functional/performance model of the hardware in C++ or System C - Fitting curves and running trendline analysis using R - Analyzing the performance characteristics of emerging workloads, including those from AI language models and large-scale distributed systems Required Qualifications: - Strong skills in C++ and/or SystemC - Strong skills in Python or other scripting languages - Experience with automation, scripting, and performance tools - Experience with performance benchmarks: analysis and optimization - Experience developing and correlating performance/simulation models - Experience in Excel, including Visual Basic, Pivot Tables, Macros - Experience in R statistical package - Experience using hardware performance counters - Basic understanding of computer systems performance principles, e.g. Amdahl's Law, Queuing Theory, mean value analysis - Understanding of CPU microarchitecture - Comfortable in using a Linux development environment - Excellent troubleshooting and problem-solving skills - Familiarity with the architectural structure and computational demands of AI language models - Understanding of or experience with performance analysis in large-scale compute environments - Currently pursuing a PhD in Electrical Engineering, or Computer Engineering, or related field. Master's degree will also be considered Required Skills: C++, SystemC, Python Important Skills: Performance benchmarks, Performance analysis, Excel, R statistical package, Linux development Nice-to-Have Skills: Troubleshooting skills, CPU microarchitecture, performance principles, AI models Benefits: Premium medical, dental, and vision insurance, Mentorship and on-the-job training from industry experts, Ergo friendly desk set-up, Vibrant game rooms to take a break and bond with colleagues, Micro-kitchens with a variety of healthy snacks, espresso, and refreshing drinks