Job Summary:The primary purpose of the AI Server / Rack Thermal Engineer (focused on L10/L11 execution) is to own the thermal profile validation, cooling efficiency optimization, and fluid-dynamics performance testing of integrated AI rack systems on the factory floor. This role ensures that fully assembled, high-density AI clusters operate within safe temperature parameters and that advanced liquid-cooling hardware-such as Coolant Distribution Units (CDUs), dripless quick-disconnect valves, and direct-to-chip water blocks-functions flawlessly under peak compute loads before shipping to the customer.
Duties and Responsibilities:- Validate liquid cooling performance for AI server and rack systems by monitoring and analyzing coolant flow, temperature, pressure, and other key telemetry data to ensure cooling loops and related components operate within engineering specifications. Identify performance abnormalities and collaborate with engineering teams to optimize cooling efficiency, system stability, and reliability.
- Conduct thermal profiling and burn-in testing under high-compute and high-power workloads to evaluate AI server and rack thermal performance. Analyze temperature, power, airflow, coolant, and component-level data to verify that critical hardware remains within defined thermal limits and identify potential performance or reliability issues.
- Investigate thermal failures, overheating events, abnormal temperature conditions, and component hotspots using system telemetry, test results, and engineering analysis. Determine root causes and implement corrective actions to improve cooling performance, mitigate thermal risks, and prevent recurring issues.
- Calibrate and optimize cooling-control parameters, including fan-speed curves, pump controls, temperature thresholds, and sensor responses, based on system workload and environmental conditions. Partner with firmware and hardware engineering teams to achieve effective thermal management while balancing cooling performance, system stability, and power efficiency.
- Manage and document thermal-related engineering changes, defects, test findings, root causes, and corrective actions throughout product development and validation. Coordinate with R&D, NPI, manufacturing, quality, and other engineering teams to ensure thermal issues are properly tracked, resolved, validated, and incorporated into product or process improvements.
Education:- Bachelor of Science (BS) Degree in Mechanical Engineering (with a heavy, verified specialization in thermodynamics, fluid mechanics, and heat transfer) or Aerospace Engineering (focusing on thermal sciences and fluid dynamics) or Thermal / Energy Engineering.
Experience:- 2+ years of Liquid Cooling & Fluid Dynamics Testing
- 2+ years of Full-System Thermal Validation & Hardware Stress Testing
- 1+ year of Thermal Failure Analysis (FA) & Diagnostic Instrumentation
- 1+ year of BMC / BIOS System Telemetry & Control Tuning
