Software Engineer, TT-Distributed
Tenstorrent2 months ago
Toronto, CanadaIntern / Entry Level / Mid Level / Senior / Staff+
Responsibilities
- Architect, implement, and optimize distributed software systems coordinating computation and communication across AI accelerator and CPU clusters.
- Design and build distributed APIs for data-parallel and tensor-parallel AI workloads.
- Use MPI-based technologies and related frameworks to scale programming models across hosts and compute nodes.
- Develop IPC, inter-node socket, and distributed communication primitives for reliable, high-performance systems.
- Build and maintain testing, debugging, profiling, and monitoring tools for large-scale distributed workloads.
- Collaborate with model and systems teams on cluster bring-up.
Requirements
- Strong C or C++ engineering skills with solid foundations in systems programming, operating systems, and distributed systems principles.
- Understanding of distributed computing, including IPC, socket programming, and cluster resource coordination.
- Ability to reason about scalability, fault tolerance, and performance across multi-node environments.
- Interest in developing deep technical expertise in large-scale distributed AI infrastructure.
Benefits
- Hybrid work arrangement based in Santa Clara, California; Austin, Texas; or Toronto, Ontario.
- Competitive compensation package and benefits.
- Candidates at various experience levels are considered, with leveling determined during the interview process.
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.