Mechanical Engineer, Hardware Systems

The role

You will define the physical design of AI inference hardware from the accelerator through the server to the rack. You will own electromechanical design, system configuration, and server and rack integration.

What you will do

• Own the electromechanical design of inference hardware including form factor, thermal solution, airflow, connectors, cabling, and power and thermal envelope.
• Build the mechanical definition of assembly structure and BOM.
• Identify assembly, cooling, and serviceability problems before parts are ordered.
• Define mechanical integration of compute, host platform, networking, and power in the chassis.
• Validate airflow and thermals with the system fully populated.
• Design for serviceability by a technician in a live rack.
• Set rack configuration, power distribution layout, cabling, weight, blanking plan, and mounting approach.
• Own drawing and BOM releases, manufacturability, and supplier engineering reviews.
• Run bring-up and validation on real hardware in the lab.
• Own mechanical and thermal qualification, including shock, vibration, and thermal cycling.

Required qualifications

• Six or more years, or equivalent shipped work, owning accelerator or server hardware.
• Strong mechanical design skills in SolidWorks, Creo, NX, or similar, including FEA, tolerance analysis, and design for manufacturing.
• Hands-on thermal design and validation for server or accelerator hardware.
• Experience integrating server hardware into standard chassis and racks.
• Electrical fluency to read schematics and work with electrical engineers on power and interconnect integration.
• Experience directing external design or manufacturing partners.

Nice to have

• Direct experience turning industrial design concepts and appearance models into production mechanical designs.
• Experience shipping hardware to external customers, including certification, documentation, and service obligations.
• Experience with soft and hard tooling decisions and fixture and test setup design with an ODM or contract manufacturer.
• Experience integrating liquid cooling into server or rack systems.
• Experience designing to Open Compute Project or other open modular server and rack architectures.

About the company

Normal is an applied AI company solving problems in AI and silicon. They build foundational hardware and software for the semiconductor industry, critical AI infrastructure, and broader systems.