Job Description
NPI Engineer, Thermal Location: Santa Clara, CA Ladder: Hardware Design Travel: Approximately 20% Role Overview At Nexthop AI, our thermal solutions are as complex as the silicon they cool. We are looking for a Hardware Product Engineer to act as the ultimate technical authority for our Direct-to-Chip (D2C) and rack-level cooling systems. This role sits within the Hardware Design Ladder and is responsible for the physical realization of our hardware—from the initial equipment selection at the factory to the final data sign-off before a product reaches the customer.
Key Responsibilities 1. Strategy, Selection & Buyoff
Critical Vendor Portfolio: Drive our thermal solutions vendor portfolio by auditing, assessing, qualifying, and ramping each vendor and their commodity. Use technical expertise to know when a second source is critical and drive the qualification of that second source. Critical Equipment Roadmap: Research and determine and design the mandatory equipment list required to support NUDD (New, Unique, Different, Difficult) thermal designs (e.g., high-vacuum leak testers, precision TIM dispensers, robotic manifold assemblers). Equipment Buyoff (FAT/SAT): Lead Factory Acceptance Testing (FAT) and Site Acceptance Testing (SAT). You own the "Buyoff" process, ensuring equipment meets precision, repeatability, and safety standards.
2. Thermal Data Authority
Thermal Validation Lead: Identify and establish the "North Star" metrics for D2C and rack-level integration. Define what we measure, how it’s captured at the factory, and why it ensures long-term survival. NPI Milestone Leadership: Lead technical reviews for EVT/DVT/PVT milestones, ensuring all thermal exit criteria are met and documented.
3. Thermal Realization and Manufacturing
Manufacturing and Quality Integration: Design thermal test vehicles, assembly fixtures, Thermal Interface Material (TIM) application processes and equipment, ensuring our contract manufacturers have the right equipment to gather the data you require. D2C Interface Ownership: Lead the technical deployment of Direct-to-Chip cooling. You own the mechanical interface between the ASIC and the cold plate, ensuring the "physics of the contact" is repeatable across multiple PCBA projects. L10/L11 System Integration: Define the technical requirements for integrating switch chassis into liquid-cooled racks, focusing on manifold reliability and blind-mate coupling integrity. TIM Strategy: Define and validate Thermal Interface Material (TIM) application and compression standards to prevent pump-out and ensure decade-long thermal stability. New Technologies : Evaluate and vet emerging cooling technologies—such as two-phase systems or advanced heat siphons—to determine technical and operational fit.
4. Reliability & Qualification Standards
Qualification Architecture: Design and execute long-term reliability plans for cold plates, heatsinks, and fans, including Accelerated Life Testing (ALT), thermal shock, and vibration profiles tailored for high-density AI environments. Industry Standards: Ensure all thermal and hydraulic systems meet industry-leading reliability requirements (referencing relevant ASHRAE or ASTM protocols for liquid-cooled hardware). Mechanical Integrity: Monitor and mitigate thermomechanical stress, ensuring mounting forces on high-cost ASICs remain within specification throughout the product lifecycle.
Required Qualifications
Experience: 8+ years in Hardware Engineering, Mechanical Engineering, or Thermal Reliability with a focus on NPI. Equipment Expertise: Proven experience in determining, qualifying, and buying off high-precision manufacturing equipment for liquid-cooled or high-power electronics. Technical Authority: Experience holding "Ship/No-Ship" authority in a high-stakes hardware environment. Domain Knowledge: Expert understanding of Direct-to-Chip cooling (Cold plates, Manifolds, QDs) and the mechanics of Thermal Interface Materials. Education: BS/MS in Mechanical Engineering, Thermal Science, or a related field.
What Success Looks Like
Data-Driven Authority: You have established the "North Star" metrics (e.g., BLT, contact pressure, and flow rates) so clearly that every NPI milestone is cleared with indisputable data, ensuring zero units leave the factory with latent thermal defects. Zero Thermal Degradation in the Field: Your TIM application strategies and mechanical interface standards have eliminated "TIM pump-out" and mounting force excursions, guaranteeing decade-long stability for high-cost switch ASICs. A Robust, De-Risked Supply Chain: You have moved beyond single-source dependencies by technically qualifying and ramping a resilient portfolio of cold plate and 3DVC vendors that meet our exacting safety and performance standards.