Performance Architect, AI HW

Tenstorrent is a leader in cutting-edge AI technology, focused on revolutionizing performance and cost efficiency. As an AI Performance Architect, you will model, analyze, and optimize AI workloads on the Tensix architecture, connecting architecture, software, and RTL to enhance efficiency and scalability in next-generation AI systems. Responsibilities Benchmark and analyze complex AI workloads across single and multi-node hardware configurations to guide next-gen architecture Develop and maintain performance models, simulators, and micro-benchmark suites to drive feature evaluation and design optimization Conduct detailed PPA (Performance, Power, Area) studies to assess design tradeoffs and inform hardware-software co-design decisions Collaborate closely with RTL, Compiler, and Runtime teams to instrument and correlate performance models with silicon results Skills Deeply analytical engineer with strong intuition for AI workload behavior and system-level performance bottlenecks Experienced in C++ and Python for simulation, modeling, and performance analysis across heterogeneous compute systems Adept at bridging software and hardware teams—translating deep learning workloads into architectural insight and measurable design tradeoffs Curious, data-driven, and comfortable pushing the limits of efficiency, scalability, and accuracy in high-performance AI systems Benchmark and analyze complex AI workloads across single and multi-node hardware configurations to guide next-gen architecture Develop and maintain performance models, simulators, and micro-benchmark suites to drive feature evaluation and design optimization Conduct detailed PPA (Performance, Power, Area) studies to assess design tradeoffs and inform hardware-software co-design decisions Collaborate closely with RTL, Compiler, and Runtime teams to instrument and correlate performance models with silicon results Benefits Highly competitive compensation package and benefits Company Overview Tenstorrent develops AI hardware and software solutions for data processing and machine learning application. It was founded in 2016, and is headquartered in Toronto, Ontario, CAN, with a workforce of 501-1000 employees. Its website is