Hardware - Thermal Engineer
FuriosaAI · Hwaseong(Dongtan), South Korea · Seoul, South Korea
Infrastructureonsite
At a glance
Highlights
- Build energy-efficient AI inference hardware to solve AI's cost crisis.
- Own thermal design from NPU package through PCIe cards to servers.
- Ship mass-production silicon with global partners like TSMC, Broadcom.
Ideal candidate
Proactive thermal engineer with data-center hardware experience who thrives collaborating across electrical and mechanical teams to deliver efficient, reliable AI systems.
Requirements
- Use CFD to simulate heat transfer and fluid flow
- Design active and passive cooling solutions including heatsinks, fans, and liquid cooling cold plates
- Evaluate NPU card thermal performance using temperature recorders, FLIR camera, thermocouples
- Collaborate with electrical, mechanical, and manufacturing teams to integrate thermal solutions
- Experience with GPU/NPU card or datacenter server development
- Business-level English communication
Lab profile
About FuriosaAI
Builds high-performance, high-efficiency AI compute for the Inference Era.
What they build
- AI inference accelerators
- High-efficiency AI compute hardware
Known for
- Energy-efficient AI chip architecture
- High-performance AI inference
- AI compiler development
Key facts
- Founded in 2017
- Offices in Korea and Silicon Valley
- Compiler-focused R&D lab in Lisbon
Posted · Last seen