Tenstorrent is leading the industry on cutting-edge AI technology, revolutionizing performance expectations, ease of use, and cost efficiency. With AI redefining the computing paradigm, solutions must evolve to unify innovations in software models, compilers, platforms, networking, and semiconductors. Our diverse team of technologists have developed a high performance RISC-V CPU from scratch, and share a passion for AI and a deep desire to build the best AI platform possible. We value collaboration, curiosity, and a commitment to solving hard problems. We are growing our team and looking for contributors of all seniorities.

We are seeking a highly experienced Principal Power Systems Architect to define and deliver next-generation power systems for high-density AI accelerator racks using 800VDC distribution. This role owns the power architecture from the data-center electrical interface through AC/DC conversion, high-voltage DC distribution, DC/DC conversion, rack busbars, protection, monitoring, and accelerator power delivery. You will lead architecture and execution across electrical, mechanical, thermal, systems, firmware, manufacturing, facilities, and data-center engineering teams to enable scalable 200 kW+ racks and beyond.

This role is hybrid, based out of Toronto, Canada, Santa Clara, California or Austin, Texas.

We welcome candidates at various experience levels for this role. During the interview process, candidates will be assessed for the appropriate level, and offers will align with that level, which may differ from the one in this posting.

Who You Are

You hold a BS or MS in Electrical Engineering, Power Electronics, or a related field, with 15+ years of experience in power electronics, power systems, or high-power electrical engineering.
You have architected and developed high-power AC/DC and DC/DC conversion systems, three-phase AC systems, high-voltage DC distribution, and high-current busbars for complex products or infrastructure.
You have deep knowledge of converter topologies, power semiconductors (Si, SiC, and GaN), magnetics, capacitors, connectors, protection devices, current sensing, thermal management, EMI/EMC, grounding, and isolation.
You are skilled in system-level efficiency, transient, thermal, power-integrity, and fault analysis, and have hands-on experience taking complex power systems from architecture and prototype through validation and production.
You can serve as a technical authority: set roadmaps, make system tradeoffs, lead design reviews, mentor engineers, and guide internal teams, suppliers, and partners.

What We Need

Define an end-to-end power architecture from facility AC distribution through conversion, 800VDC generation and distribution, rack busbars, intermediate and point-of-load conversion, and AI accelerator power delivery; scale the design from approximately 200 kW to 400 kW+ per rack.
Architect high-efficiency AC/DC and DC/DC conversion, evaluating distribution voltages, conversion topologies, centralized versus distributed designs, transient response, power quality, losses, thermal performance, and supplier solutions.
Specify safe, reliable high-voltage DC distribution, including busbars and connectors, isolation and grounding, protection and fault zones, DC arc interruption, pre-charge and discharge, interlocks, emergency shutdown, serviceability, and applicable regulatory requirements.
Lead system integration across data-center infrastructure, rack mechanics, cooling, and accelerator platforms; establish efficiency and power-density targets, electrical interfaces, validation plans, and requirements for power integrity, EMI/EMC, reliability, and thermal performance.
Drive the architecture from concept through production: lead detailed design and reviews, prototype bring-up, characterization, safety and fault testing, supplier qualification, DFM, manufacturing transition, and the long-term power roadmap for AI infrastructure.

What You Will Learn

How to define the production-ready 800VDC power architecture and complete facility-to-accelerator power chain for next-generation AI racks.