Tenstorrent is seeking a Performance Architect for AI hardware to model and optimize architectures for productive AI workloads, shaping next-generation accelerators. You will evaluate AI workloads on single and multi-node setups, build simulators and models, run PPA studies, and collaborate with RTL, compiler, and runtime teams to align performance results with silicon.
This full-time role offers remote-friendly options and a direct impact on future fabric design and system-level performance