Build low-level kernels for Tenstorrent AI hardware in a hybrid Toronto role, using strong C/C++ and performance engineering skills.
As a Low-Level Software Engineer on Tenstorrent’s LLK team, you will create software primitives directly above the hardware ISA. The work connects software with AI hardware, supporting efficient model bring-up and execution. Candidates at various experience levels are considered and assessed accordingly.
Key Responsibilities:
Design low-level kernels exposing Tenstorrent AI hardware capabilities
Implement software primitives for AI workloads
Profile bottlenecks and optimize performance
Validate improvements across the low-level software stack
Collaborate with hardware, runtime, and operations engineers