Etched is building AI chips that are hard-coded for individual model architectures. Our first product (Sohu) only supports transformers, but has an order of magnitude more throughput and lower latency than a B200. With Etched ASICs, you can build products that would be impossible with GPUs, like real-time video generation models and extremely deep & parallel chain-of-thought reasoning agents.
Job Summary
Our Platform Team designs the servers and systems that deliver our chips’ full potential. We are seeking a Head of Platform Mechanical & Thermal Engineering to lead all aspects of mechanical architecture, advanced cooling, and CAD infrastructure for next-generation high-power density ASIC systems.
This leader will build and scale the mechanical and thermal engineering organization, with a strong focus on liquid cooling technologies and rack-level thermal management. Siemens NX is our standard 3D CAD platform, and you will also drive the deployment of industry-leading CFD and rack simulation tools to ensure performance, manufacturability, and reliability at datacenter scale.
Key Responsibilities
Leadership & Team Growth
Build, mentor, and scale a team of mechanical and thermal engineers.
Define hiring plans and technical standards for advanced cooling and mechanical design.
Foster a culture of engineering rigor and cross-disciplinary collaboration.
Mechanical & Thermal Architecture
Own the design of server enclosures, modules, and racks optimized for high-power ASICs.
Drive liquid cooling solutions (cold plates, manifolds, quick-disconnects, CDU integration) as well as air-assisted hybrid cooling where applicable.
Ensure mechanical designs meet standards for manufacturability, serviceability, and reliability under extreme thermal loads.
Tools & Infrastructure
Deploy and optimize Siemens NX for CAD/PLM workflows, with integrated libraries and release processes.
Establish and scale simulation infrastructure, including:
Flowtherm and Ansys Icepak for detailed CFD of component and system thermal behavior.
MacroFlow for rack-level and datacenter fluid dynamics modeling.
Standardize validation workflows linking simulation to hardware measurements.
Validation & Reliability
Define test plans for thermal performance, fluid integrity, and long-term reliability of liquid cooling systems.
Oversee lab infrastructure for thermal and mechanical validation at both module and rack scale.
Partner with electrical and system validation teams to ensure holistic system readiness.
Cross-Functional & External Collaboration
Collaborate closely with silicon, electrical, and system engineers to co-optimize cooling with chip and board power delivery.
Engage with suppliers, ODMs, and datacenter partners to align design with deployment environments.
Represent mechanical and thermal engineering in executive reviews, providing visibility into risks, milestones, and resources.
You may be a good fit if you have
10+ years of experience in mechanical and thermal engineering for high-performance computing systems, with at least 5+ years in leadership roles.
Proven expertise in liquid cooling architectures for high-power density ASICs or GPUs.
Proficiency with Siemens NX for 3D CAD; experience scaling CAD/PLM environments across teams.
Hands-on experience with Flowtherm, Ansys Icepak, and MacroFlow for CFD and rack-level thermal modeling.
Strong record of bringing complex server or datacenter platforms from concept through production.
Deep understanding of thermal validation, fluid integrity testing, and mechanical reliability for liquid-cooled systems.
Bachelor’s or Master’s in Mechanical Engineering, Thermal Engineering, or related field .
Base Salary Compensation
$225,000 - $275,000
Benefits
Full medical, dental, and vision packages, with generous premium coverage
Housing subsidy of $2,000/month for those living within walking distance of the office
Daily lunch and dinner in our office
Relocation support for those moving to San Jose (Santana Row)
How we’re different
Etched believes in the Bitter Lesson. We think most of the progress in the AI field has come from using more FLOPs to train and run models, and the best way to get more FLOPs is to build model-specific hardware. Larger and larger training runs encourage companies to consolidate around fewer model architectures, which creates a market for single-model ASICs.
We are a fully in-person team in San Jose (Santana Row), and greatly value engineering skills. We do not have boundaries between engineering and research, and we expect all of our technical staff to contribute to both as needed.