Performance Architect, AI HW
Tenstorrent · Santa Clara, California, United States
About this role
**Performance Architect, AI HW** **About Tenstorrent** Leading the industry on cutting-edge AI technology, revolutionizing performance expectations, ease of use, and cost efficiency. Our diverse team has developed a high-performance RISC-V CPU from scratch with a passion for building the best AI platform possible. **The Role** The Tensix team is building the high-performance compute fabric that powers Tenstorrent's AI and ML workloads. As an AI Performance Architect, you will model, analyze, and optimize how real AI workloads run on the Tensix architecture, shaping future hardware features and ensuring every design decision delivers measurable performance gains. **Location** Hybrid: Toronto, ON | Austin, TX | Santa Clara, CA | Remote **Who You Are** • 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 • Curious, data-driven, and comfortable pushing the limits of efficiency, scalability, and accuracy **What You'll Do** • Benchmark and analyze complex AI workloads across single and multi-node hardware configurations • Develop and maintain performance models, simulators, and micro-benchmark suites • Conduct detailed PPA (Performance, Power, Area) studies to assess design tradeoffs • Collaborate with RTL, Compiler, and Runtime teams to instrument and correlate performance models **What You'll Learn** • Advanced modeling techniques for large-scale AI systems and distributed performance analysis • How architectural choices propagate through the software stack to custom AI accelerators • Emerging deep learning trends and their impact on compute architecture design • How to define and validate performance features that translate to real-world AI workload gains **Compensation** $100k - $500k (including base and variable compensation targets). Experience, skills, education, background and location impact the actual offer. *Equal opportunity employer. Contingent upon eligibility to access U.S. export-controlled technology.*
Listing freshness
CronJobs last confirmed this listing 15h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.