Software Engineer, Acceleration Kernel Development
Tenstorrent2 months ago
Toronto, CanadaIntern / Entry Level / Mid Level / Senior / Staff+
Responsibilities
- Build and optimize compute kernels for parallel machine learning and high-performance workloads.
- Analyze and tune instruction-level performance across latency, memory, and bandwidth.
- Collaborate with ML engineers to integrate kernel optimizations into production.
- Debug, profile, and maintain a fast and reliable low-level software stack.
- Integrate kernel work into ML frameworks and real-world training pipelines.
- Tune performance on advanced hardware architectures in collaboration with hardware engineers.
Requirements
- Strong expertise in C and C++ development.
- Experience building and optimizing parallel compute kernels for ML or high-performance workloads.
- Ability to analyze and tune instruction-level performance, including latency, memory, and bandwidth.
- Interest in high-performance code, parallel algorithms, low-level programming, and hardware optimization.
- Ability to work collaboratively in a complex, fast-moving environment.
Benefits
- Hybrid work arrangement based in Toronto, Ontario.
- Competitive compensation package and benefits.
- Candidates may be assessed and leveled according to their experience during the interview process.
- Employment is contingent on eligibility to access U.S. export-controlled technology.
About Tenstorrent
Tenstorrent builds AI compute hardware and RISC‑V CPU technology for companies developing training and inference workloads in data centers and at the edge. The business sells accelerator cards and systems with a full software stack, and licenses RISC‑V CPU IP. Founded in 2016 and headquartered in Toronto, it is privately held and led by semiconductor architect Jim Keller.