About the role#
This internship is part of the team that ensures models run on Tenstorrent hardware at scale. You will work across several areas including kernels, model optimization, inference servers, runtime engines, and distributed system scale-out. We match interns to specific teams based on their background and interests.
What you'll do#
- Develop high-performance kernels for hardware.
- Optimize machine learning models like LLMs, vision, and image generation architectures.
- Build and optimize inference server serving-side components.
- Create software engines to manage memory, task scheduling, and code execution.
- Coordinate communication between devices in distributed AI systems.
- Develop tools for memory planning, profiling, debugging, and emulation to optimize AI models.
What you'll need#
- Currently pursuing a BS, MS, or PhD in Computer Science, Computer Engineering, Physics, Mathematics, or a related field.
- Coursework or projects in parallel processing, machine learning, or distributed systems.
- High comfort level using AI and agentic flows.
- Experience with model quantization, kernel fusion, or other optimization techniques.
- Hands-on experience with PyTorch for model experimentation or deployment.
- Proficiency in C/C++ or kernel development in languages like CUDA.
- Experience with Python and at least one ML framework such as PyTorch, TensorFlow, or JAX.
- Knowledge of RTL or HDL is a plus.
Location & details#
- This role is on-site in Austin, Texas or Santa Clara, California.
- Internships are available for Winter, Summer, and Fall 2027 terms.
- This is a paid, full-time position.
- Employment is contingent upon eligibility to access U.S. export-controlled technology.
About Tenstorrent
Tenstorrent builds computers designed for artificial intelligence. The company focuses on computer architecture, ASIC design, and RISC-V technology. Founded in 2016, it maintains a global presence with offices in North America, Europe, and Asia. It operates as a privately held organization with over 1,000 employees.
How to get in at Tenstorrent
Applying early at Tenstorrent gives you a distinct advantage because recruiters review applications before the pile grows. Intern Insider sends an instant alert the moment a role matching your target is published, so you can submit your materials among the first candidates. Getting your application in early helps ensure your profile is seen while the team is still actively reviewing initial submissions. You can use Intern Insider to identify the recruiters behind Tenstorrent roles to reach out directly for a referral or to ask specific questions about the position. Connecting with a recruiter can materially improve your response rates compared to submitting through a general portal. This direct approach shows you are serious about the work and helps you stand out in a competitive field.
