Principal Power Systems Architect - AI Accelerator Systems
2 days agoHeadSalary: 100K - 500KToronto, Canada; Santa Clara, California; Austin, TexasHybridEngineeringJobs by Tenstorrent
TenstorrentVisit Tenstorrent website
Tenstorrent is an AI-computing company that sells AI hardware and licenses AI and RISC-V intellectual property.
Series ERecently funded364 current maintainers296 active leads42 new active leads111 lead step-downs8 early lead departures
Toronto, Canada
Funding history
Investors
About Tenstorrent
Tenstorrent builds computers for AI, including AI processors, scalable server systems, and open-source software and compiler tooling. It also licenses AI and RISC-V IP for customers building customized silicon.
Skills
About the Role
You will define the end-to-end power architecture for AI accelerator racks using 800VDC distribution, architect AC/DC and DC/DC conversion, specify safe high-voltage distribution, lead system integration and drive the architecture from concept through production.
Requirements
- BS or MS in Electrical Engineering, Power Electronics or related field
- 15+ years in power electronics, power systems or high-power electrical engineering
- Architected high-power AC/DC and DC/DC systems, three-phase AC, HVDC distribution and busbars
- Deep knowledge of converter topologies, power semiconductors (Si, SiC, GaN), magnetics, EMI/EMC, grounding and isolation
- Experience taking power systems from prototype through validation and production
- Ability to set roadmaps, lead design reviews and mentor engineers
Responsibilities
- Define end-to-end power architecture from facility AC to accelerator power delivery, scaling 200 kW to 400 kW+ per rack
- Architect high-efficiency AC/DC and DC/DC conversion
- Specify safe high-voltage DC distribution including busbars, isolation, grounding and protection
- Lead system integration across data-center infrastructure, rack mechanics, cooling and accelerator platforms
- Drive architecture through design reviews, prototype bring-up, testing, supplier qualification, DFM and manufacturing transition
