Thermal Design & Validation Engineer

Advanced Micro Devices, Inc•Secaucus, NJ

About The Position

As a Thermal Design & Validation Engineer in the Data Center Platform Engineering (DPEG) Thermal Mechanical Engineering team, you will design, simulate, validate, and qualify liquid cooling solutions for AMD's next-generation AI and Data Center GPU products. Spanning cold plate design, liquid cooling architecture, thermal-mechanical analysis, CFD simulation, and lab validation, you'll partner with thermal architects, package and board designers, system engineers, manufacturing, and external suppliers to deliver high-performance, reliable, and manufacturable cooling solutions from concept through production.

Requirements

BS, MS, or PhD in Mechanical Engineering or related discipline.
Proficiency with CAD software (Creo and/or SolidWorks).
Python, MATLAB, LabVIEW, or similar tools for automation, data analysis, DOE, and statistical methods.
Strong problem-solving, debugging, and root-cause skills, with familiarity in OCP and modern liquid-cooled AI infrastructure.

Nice To Haves

Domain expertise in heat transfer, fluid mechanics, and electronics cooling, with experience validating liquid cooling for high-power electronics — ideally AI, HPC, or Data Center server platforms.
Cold plate design and thermal interface management, including manufacturing processes such as machining, brazing, skiving, friction stir welding, and additive manufacturing.
CFD analysis with Icepak, FloTHERM, Ansys Fluent, or similar tools.
1D flow network modeling, with a strong grasp of pressure drop, flow distribution, and coolant performance optimization.
FEA for structural and thermo-mechanical analysis, plus GD&T, manufacturing tolerances, and assembly processes.
Thermal and mechanical validation of cold plates and rack-level cooling systems, including lab instrumentation, telemetry, data acquisition, and analysis.
Lead end-to-end liquid cooling validation, including thermal, hydraulic, leak, and qualification testing to support product release.

Responsibilities

Design and develop cold plates and liquid cooling components for AMD Data Center GPU platforms, driving hardware development from concept through validation and production release.
Run CFD simulations (Icepak or equivalent) and 1D flow network models to optimize thermal performance, coolant distribution, pressure drop, and flow balance at component, server, and rack level.
Perform thermal-mechanical analysis of cold plate assemblies — mounting load, tolerance stack-up, flatness, warpage, and interface contact — to ensure performance and reliability.
Plan and execute validation for cold plates, manifolds, tubing assemblies, and full liquid cooling systems, including flow, pressure drop, thermal resistance, leak, and reliability testing.
Correlate test data with simulation, identify design optimizations, and drive root-cause analysis and corrective actions for thermal, mechanical, and manufacturing issues.
Communicate results through technical reports and design reviews.