Founding Mechanical Engineer for AI Inference Hardware

Normal Computing Corporation; Palo Alto (CA); On-site; USD 120,000 - 160,000; Full time

Job summary

Normal Computing is building AI inference hardware based on Thermo In-Memory Computing. As the founding mechanical engineer, you will define physical design for hardware from accelerator to rack, shaping form factor, cooling, and serviceability.

You will work with silicon, systems, and external partners to bring designs into production. You will own mechanical integration of compute, host platform, networking, and power, ensuring proper airflow and thermals while enabling serviceability in live

Qualifications

• Requires 6+ years shipping accelerator or server hardware from prototype to production.
• Strong CAD skills and the ability to release manufacturable drawings.
• Hands-on thermal design and verification with practical lab work.
• Experience integrating server hardware into standard chassis and racks.

Responsibilities

• Own electromechanical design from concept to deployable product including form factor and thermal envelope.
• Define mechanical integration of compute, host, networking, and power in chassis.
• Validate airflow and thermals with fully populated systems in lab setups.
• Coordinate with external design and manufacturing partners and releases.
• Lead build readiness, BOM control, and supplier reviews.
• Develop test specs for thermal and mechanical qualification and safety alignment.

Skills

Accelerator hardware design

Server hardware design

CAD software

Thermal design

FEA

Vendor management

Education

Bachelor's degree in Mechanical Engineering

Tools

SolidWorks

Creo

NX

FEA tools

Job description

Normal Computing is building AI inference hardware based on Thermo In-Memory Computing. As the founding mechanical engineer, you will define physical design for hardware from accelerator to rack, shaping form factor, cooling, and serviceability.

You will work with silicon, systems, and external partners to bring designs into production. You will own mechanical integration of compute, host platform, networking, and power, ensuring proper airflow and thermals while enabling serviceability in live