Principal Software Engineer
Toronto, San Francisco Bay Area, Austin
$100,000 - $500,000/yearly
Staff
About the role
Who you are
- A technical leader with deep expertise in C++ and system-level performance, capable of setting direction and mentoring others in writing highly efficient code
- Someone who sees the big picture of ML frameworks, understands how PyTorch, TensorFlow, JAX operate under the hood, and can steer architectural decisions that impact multiple layers of the stack
- Comfortable getting deep into performance profiling and solving problems on other levels of the stack
- Enjoy working closely with experts across hardware, high performance software, ML and compilers
What the job involves
- As a Principal Software Engineer on the ML Frameworks team at Tenstorrent, you will define and drive the architecture that enables machine learning models to run at breakthrough performance on our custom silicon
- You will work across the entire software stack, from compilers to runtime to frameworks like PyTorch, while shaping the abstractions and strategies that unlock the full potential of our hardware
- This is a role for someone who thrives on solving difficult performance problems and influencing the direction of AI frameworks at scale
- This role is hybrid, based out of Toronto, ON; Austin, TX; Santa Clara, CA, with the opportunity to be remote on a candidate by candidate basis
- During the interview process, candidates will be assessed for the appropriate level, and offers will align with that level, which may differ from the one in this posting
- Make it easy for ML engineers and compilers to bringup and optimize new models
- Make it easy for kernel developers to introduce new operations
- Extend and optimize TT-NN to enable lazy evaluation and operation fusion
- Work across all layers with hardware, runtime, compiler, kernels, inference and training teams to know what's possible and what's needed
- What You Will Learn:
- How ML frameworks and compilers connect at the system level
- How to co-design software frameworks with custom silicon architectures
- How model inference and training work under the hood, from memory layout to operator fusion
- What it takes to build infrastructure that supports fast iteration in research and production
About Tenstorrent
Computer Hardware Manufacturing
501-1000
Tenstorrent is a next-generation computing company that builds computers for AI.
Headquartered in the U.S. with offices in Austin, Texas, and Silicon Valley, and global offices in Toronto, Belgrade, Seoul, Tokyo, and Bangalore, Tenstorrent brings together experts in the field of computer architecture, ASIC design, RISC-V technology, advanced systems, and neural network compilers. Tenstorrent is backed by Eclipse Ventures and Real Ventures, Archerman Capital, Samsung Catalyst Fund, and Hyundai Motor Group among others.
Join us: www.tenstorrent.com/careers.
Principal Software Engineer
Toronto, San Francisco Bay Area, Austin
$100,000 - $500,000/yearly
Staff
About the role
Who you are
- A technical leader with deep expertise in C++ and system-level performance, capable of setting direction and mentoring others in writing highly efficient code
- Someone who sees the big picture of ML frameworks, understands how PyTorch, TensorFlow, JAX operate under the hood, and can steer architectural decisions that impact multiple layers of the stack
- Comfortable getting deep into performance profiling and solving problems on other levels of the stack
- Enjoy working closely with experts across hardware, high performance software, ML and compilers
What the job involves
- As a Principal Software Engineer on the ML Frameworks team at Tenstorrent, you will define and drive the architecture that enables machine learning models to run at breakthrough performance on our custom silicon
- You will work across the entire software stack, from compilers to runtime to frameworks like PyTorch, while shaping the abstractions and strategies that unlock the full potential of our hardware
- This is a role for someone who thrives on solving difficult performance problems and influencing the direction of AI frameworks at scale
- This role is hybrid, based out of Toronto, ON; Austin, TX; Santa Clara, CA, with the opportunity to be remote on a candidate by candidate basis
- During the interview process, candidates will be assessed for the appropriate level, and offers will align with that level, which may differ from the one in this posting
- Make it easy for ML engineers and compilers to bringup and optimize new models
- Make it easy for kernel developers to introduce new operations
- Extend and optimize TT-NN to enable lazy evaluation and operation fusion
- Work across all layers with hardware, runtime, compiler, kernels, inference and training teams to know what's possible and what's needed
- What You Will Learn:
- How ML frameworks and compilers connect at the system level
- How to co-design software frameworks with custom silicon architectures
- How model inference and training work under the hood, from memory layout to operator fusion
- What it takes to build infrastructure that supports fast iteration in research and production
About Tenstorrent
Computer Hardware Manufacturing
501-1000
Tenstorrent is a next-generation computing company that builds computers for AI.
Headquartered in the U.S. with offices in Austin, Texas, and Silicon Valley, and global offices in Toronto, Belgrade, Seoul, Tokyo, and Bangalore, Tenstorrent brings together experts in the field of computer architecture, ASIC design, RISC-V technology, advanced systems, and neural network compilers. Tenstorrent is backed by Eclipse Ventures and Real Ventures, Archerman Capital, Samsung Catalyst Fund, and Hyundai Motor Group among others.
Join us: www.tenstorrent.com/careers.