Thermal Process Engineer

Company Overview

We are a high-growth startup building next-generation high‑performance switching systems for hyperscale and AI data centers. Our platforms power large-scale cloud infrastructure, GPU clusters, and high-density compute environments where performance, reliability, and thermal efficiency are critical to customer operations.

Position Summary

The Liquid Cooling Process Engineer owns the manufacturing process definition, validation, and scaling of liquid-cooled network products in conjunction with NH engineering. This role bridges thermal design, mechanical design, manufacturing engineering, reliability, and supply chain to ensure liquid-cooling solutions—cold plates, manifolds, hoses, quick-disconnects, and TIMs—are repeatable, leak-free, thermally efficient, and production-scalable.

The role is critical to enabling >50–100 kW per rack architectures, supporting next-generation AI fabrics and ultra-high-bandwidth network switches without compromising reliability or serviceability.

Key Responsibilities

Process Definition & Development

Define end-to-end manufacturing processes in close collaboration with engineering for:

Direct-to-chip cold plates

Manifolds and distribution plates

Tubing, hoses, and quick-disconnects (QDs)

TIM application (grease, PCM, gap fillers)

Develop process flow diagrams, control plans, and work instructions

Ensure processes are DFM/DFA/DFS compliant and serviceable in field environments

NPI Execution (EVT → DVT → PVT → MP)

Enable fast prototyping and rapid iterative development cycles

Drive development of DFMEA (Design Failure Mode Effects and Analysis) with engineering

Support thermal hardware from early EVT through HVM ramp

Identify and mitigate process risks:

Leak paths

Torque variation

Flatness and coplanarity

Particulate contamination

Lead process validation builds and golden line definition

Partner with ODMs to ensure manufacturability at scale

Assembly, Tooling & Automation

Specify and qualify:

Torque tools and sequencing strategies

Dispensing systems for TIMs and sealants

Pressure and leak-test equipment (air, helium, liquid)

Drive semi-automated and automated solutions for:

Cold-plate installation

Hose routing and retention

QD (Quick Disconnect) engagement verification

Define poka-yoke mechanisms to prevent mis-builds

Quality, Reliability & Validation

Own PFMEA (Process Failure Mode Effects and Analysis) and control plans for liquid-cooling processes

Define acceptance criteria for:

Leak rate

Pressure decay

Flow resistance

Thermal performance

Support HALT/HASS, thermal cycling, vibration, and shock testing

Lead root-cause analysis for field and factory issues (leaks, clogging, corrosion)

Data, Monitoring & Continuous Improvement

Establish process KPIs:

Leak ppm

Torque Cp/Cpk

TIM thickness uniformity

Yield and rework rates

Integrate test data into MES and quality dashboards

Drive yield improvement and cost reduction through data-driven analysis

Supplier & Partner Management

Work closely with:

Cold-plate suppliers

Hose and QD vendors

TIM and sealant suppliers

ODM/OEM manufacturing teams

Qualify suppliers and define incoming quality requirements

Support dual-sourcing and cost-down initiatives

Required Qualifications

Master’s degree in Mechanical Engineering, Manufacturing Engineering, or related field

7+ years experience in manufacturing and process engineering with 2+ years of liquid cooling experience

Hands-on experience with thermal or fluid-handling hardware

Strong understanding of:

Mechanical tolerances and torque control

Assembly processes and tooling

Manufacturing quality systems

Thermodynamics

Heat transfer

Experience with liquid-cooled servers, network switches, or HPC systems

Experience working in or with startups

Preferred Qualifications

• Familiarity with:

• Cold-plate design and materials (Cu, Al, Ni plating)

• TIM characterization and dispensing

• Leak detection methods (helium mass spec, pressure decay)

• Experience working with hyperscalers or large ODMs

• Knowledge of data-center cooling architectures (DLC, CDU, facility interfaces)

• Key Competencies

• Strong hands-on manufacturing mindset

• Ability to translate thermal design into robust production processes

• Structured problem-solving and root-cause analysis

• Cross-functional communication and influence

• Comfortable operating in fast-paced NPI and ramp environments

• Success Metrics

• Leak rate at factory and in field

• Thermal performance consistency

• First-pass yield through PVT and MP

• NPI schedule adherence

• Cost and cycle-time targets achieved

• Use of automation to reduce variability and increase throughput + yield

• Why This Role Matters

• Liquid cooling is no longer optional for hyperscale networking. This role ensures liquid-cooled platforms can be manufactured safely, reliably, and at massive scale, enabling next-generation bandwidth and AI infrastructure without compromising uptime or quality.