Silicon Bring-Up (CPU/DRAM Controller/CMU/PMU 등 주요 block)
각 IPs Function Validation
CPU, DRAM, PMU, NAND, PCIe, DMA, SPI, I2C, UART, …
주요 전압 Domain LVCC 마진 평가 (by SDK version, Board version, Corner, Chip Revision)
주요 전압 domain Screen Vector 확보, 동작 전압 확보, 동작 Freq. 확보
Issue Debugging & Workaround Solution 확보
Board Bring-up (by revision) 및 Sample Sorting
ASB Board, Evaluation Board, High Speed Characteristic Test Board, GPIO Board,
Stability Test (Aging with machine & server)
Solution QA Team과 협업 및 Support
양산성 확보 (Mass Production Yield Issue 대응 및 개선, Screen Criteria 확보)
SW version up Feasibility 평가: SW Up Version Release 적합성 평가 (Margin/Function/Aging)
C, Python, Bash 와 같은 Programming Language 이해 및 활용 능력
전자회로 (반도체), 컴퓨터 구조에 대한 이해
Linux 활용 능력 (Ubuntu) 및 Device Driver (Firmware) 구현 능력
High Speed Interface (DRAM, PCIe, D2D, Ethernet 등)에 대한 이해
SOC 특성(Shmoo, LVcc, Eye Margin, Power, Temperature 등)에 대한 이해
Oscilloscope, Power Supply, Multimeter 등 측정 장비 사용 경험
Skills Required
- Understanding and ability to utilize programming languages like C, Python, and Bash
- Understanding of electronic circuits and computer architecture
What We Do
FuriosaAI designs and develops data center accelerators for the most advanced AI models and applications. Our mission is to make AI computing sustainable so everyone on Earth has access to powerful AI. Our Background Three misfit engineers with each from HW, SW and algorithm fields who had previously worked for AMD, Qualcomm and Samsung got together and founded FuriosaAI in 2017 to build the world’s best AI chips. The company has raised more than $100 million, with investments from DSC Investment, Korea Development Bank, and Naver, the largest internet provider in Korea. We have partnered on our first two products with a wide range of industry leaders including TSMC, ASUS, SK Hynix, GUC, and Samsung. FuriosaAI now has over 140 employees across Seoul, Silicon Valley, and Europe. Our Approach We are building full stack solutions to offer the most optimal combination of programmability, efficiency, and ease of use. We achieve this through a “first principles” approach to engineering: We start with the core problem, which is how to accelerate.
