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 Senior Staff / Principal Engineer to architect and deliver an intelligent thermal management control plane for next-generation AI datacenter infrastructure. As AI deployments scale to multi-100 kW racks and multi-megawatt clusters, this role will coordinate cooling across compute hardware, rack-level liquid cooling, Coolant Distribution Units (CDUs), and facility infrastructure. You will set the system architecture and lead implementation across hardware, firmware, software, mechanical engineering, and datacenter infrastructure teams.

This role is hybrid, based out of Santa Clara, California, Toronto, Canada 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 have a BS, MS, or PhD in Electrical, Mechanical, Computer, or Controls Engineering, or a related technical discipline, and 12+ years of relevant engineering experience.
You have architected and delivered complex distributed control systems, industrial automation, datacenter infrastructure, or thermal management systems, integrating multiple hardware, firmware, and software subsystems.
You bring deep knowledge of liquid-cooling systems, including CDUs, coolant distribution networks, pumps, heat exchangers, valves, and facility cooling, as well as control theory, feedback systems, PID control, system modeling, and dynamic thermal management.
You are experienced with industrial communication and management protocols such as Modbus, BACnet, OPC UA, MQTT, and Ethernet-based control networks, along with telemetry, real-time monitoring, and fault detection.
You can set technical direction, make architecture decisions, and lead complex cross-functional engineering programs from concept through integration and deployment.

What We Need

Define and lead a scalable, hierarchical thermal control-plane architecture spanning servers, racks, rows, clusters, CDUs, facility cooling loops, chillers, cooling towers, and building management systems; establish subsystem responsibilities, interfaces, APIs, protocols, and telemetry requirements.
Develop distributed, closed-loop control and optimization strategies that allocate cooling capacity and coordinate coolant temperatures, flow, pressure, pumps, valves, CDUs, and facility resources in response to workload demand and thermal conditions.
Integrate third-party CDUs and facility infrastructure, including technology cooling systems and facility water systems; establish operating envelopes, redundancy, failover, fault recovery, and coordination with BMS and industrial control systems.
Lead control software and systems engineering: define device-level interfaces and state machines, safety interlocks, fault isolation, cybersecurity, availability, monitoring, alerting, and predictive thermal management; partner with firmware and embedded teams on implementation.
Drive cross-functional system integration, validation, reliability testing, and production readiness, including thermal stability during workload changes and cooling or communications failures, and coordinate safe thermal protection or workload-throttling strategies with compute management systems.

What You Will Learn

How to establish the thermal control-plane foundation for increasingly dense AI infrastructure, from individual racks to multi-megawatt datacenter deployments.