Tenstorrent is leading the industry on cutting-edge AI technology, revolutionizing performance expectations and cost efficiency. As an AI Performance Architect, you will model, analyze, and optimize AI workloads on the Tensix architecture, ensuring design decisions deliver measurable performance gains.
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
- Tenstorrent offers a highly competitive compensation package and benefits
- This offer of employment is contingent upon the applicant being eligible to access U.S. export-controlled technology.
- As the position offered will have direct and/or indirect access to information, systems, or technologies subject to these laws, the offer may be contingent upon your citizenship/permanent residency status or ability to obtain prior license approval from the U.S. Commerce Department or applicable federal agency.
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 http://tenstorrent.com.