CPU/AI Workload Analysis Intern

About the role#

As a CPU/AI Workload Analysis Intern, you will work alongside CPU designers and performance architects to research emerging CPU workloads and analyze their impact on next-generation hardware. This role focuses on maximizing hardware performance through workload characterization, simulation, and hardware-software co-design.

What you'll do#

• Conduct research into cutting-edge CPU application trends, workload characterization, and advanced performance and power modeling techniques.
• Develop robust profiling, automation, and visualization tools to accelerate workload analysis and improve production workflows.
• Identify microarchitectural bottlenecks and reduce workloads to enable efficient simulation.
• Utilize advanced parallel computation techniques to optimize Tenstorrent hardware performance.
• Contribute to novel research and develop patentable ideas.

What you'll need#

• Currently pursuing a Ph.D. in Computer Architecture, Parallel Computing, Artificial Intelligence, Machine Learning, or a related field.
• Strong foundation in computer organization, computer architecture, parallel computation, and digital logic design.
• Hands-on experience with Linux, performance and power profiling tools, Silicon PMU profiling, and hardware performance counters.
• Proficiency in Shell scripting, Python, and C++, with experience in PyTorch, benchmarking, and targeted microbenchmarks.
• Familiarity with modern AI productivity workflows.

Location & details#

• Location: Santa Clara, California, United States.
• Modality: On-site.
• Employment type: Full-time, paid internship.
• Academic background: Computer Science, Computer Engineering, Electrical Engineering, Data Science, or Mathematics.
• Note: This position is subject to U.S. export control laws; employment eligibility may be contingent upon citizenship or permanent residency status.