ApplyBlast uses AI to match you with the right jobs, tailor your resume and cover letter, and apply automatically so you can land your dream job faster.

Features

Auto Apply Resume Optimizer Cover Letter Optimizer Interview Prep

Company

Social Media

Need Help?

team@applyblast.com

CPU Performance Architect Intern at Tenstorrent - ApplyBlast

CPU Performance Architect Intern

Tenstorrent

4 months ago

3.6 on Glassdoor

Santa Clara, California, United States

Onsite

Internship

Intern

0 applicants

View Job Listing

Apply to 100+ jobs

About this role

The CPU Performance Architect Intern at Tenstorrent will conduct research on emerging CPU workloads, develop profiling and automation tools, and identify microarchitectural bottlenecks to improve hardware performance. The role offers hands‑on experience with Linux, performance profiling, and AI workloads, while collaborating with CPU designers and software teams to influence next‑generation accelerator architecture.

Responsibilities

Conduct research on emerging CPU workloads and performance modeling
Develop profiling, automation, and visualization tools for workload analysis
Identify microarchitectural bottlenecks and propose hardware-aware optimizations

Skills

Qualifications

Ph.D. in Computer Architecture, Parallel Computing, Artificial Intelligence/Machine Learning, or related field

About Tenstorrent

tenstorrent.com

Headquarters

Toronto, Ontario, Canada

Company Size

201-500 employees

Founded

2016

View Profile

Tenstorrent is a next‑generation computing company that builds computers optimized for AI workloads. They design AI silicon and systems—leveraging RISC‑V, custom ASICs, and advanced architecture—alongside neural‑network compilers and software to accelerate training and inference. Headquartered in the U.S. with offices in Austin and Silicon Valley and global teams in Toronto, Belgrade, Seoul, Tokyo, and Bangalore, Tenstorrent brings together expertise in computer architecture, ASIC design, and compiler technology. Their hardware‑plus‑software approach targets developers, researchers, and enterprises needing scalable, efficient AI compute.