Productization & Validation Engineer
About the job
- Understand Arm architecture, AMBA bus, computer architecture, and programming.
- Be able to use programming languages such as C, Python, and Bash.
- Understand PCB schematics and basic electronic circuits, including design rules.
- Bring up first silicon, including PCIe, DRAM, and Ethernet.
- Validate the functions of the main IPs, such as PCIe, DRAM, and Ethernet.
- Evaluate LVCC of the main supply voltage domain and eye-opening margin.
- Enable high-speed interfaces such as PCIe, DRAM, and Ethernet.
- Debug issues and identify workaround solutions.
- Ensure the reliability and mass producibility of the AI accelerator through yield improvement and manufacturability.
- Provide customer technical support and perform failure analysis.
- Conduct system-level feasibility testing for software version upgrades.
- Use Linux (Ubuntu) and implement device drivers or firmware.
- Control IP at the firmware level or understand IP functions and characteristics.
- Understand signal and power integrity, including ODT, drive strength, Vref, and setup/hold timing margins.
- Have silicon validation capability for PCIe, Ethernet, UCIe, and DRAM.
About the company
FuriosaAI develops AI accelerators for data centers. Its flagship RNGD chip is a power-efficient accelerator designed to boost performance per watt for running large language models and other demanding AI workloads. The hardware is configurable with multiple processing elements to fit different workloads, and it is paired with advanced compiler technology and profiling tools to identify bottlenecks and optimize efficiency. This combination of flexible hardware and software optimization differentiates FuriosaAI from competitors, focusing on maximizing performance while keeping energy use low. The company targets data centers and enterprises that need high-performance, energy-efficient AI solutions, and aims to make AI computing more sustainable and scalable by selling its chips and related software tools and pursuing long-term contracts with large-scale customers.
Company Size
201-500
Company Stage
Series D
Total Funding
$880.8M
Headquarters
Seoul, South Korea
Founded
2017
Get referred to FuriosaAI
See people who can refer or advise you
Simplify's Take
What believers are saying
- September 3, 2026 RENEGADE summit added Samsung SDS, LG Uplus, MegazoneCloud, and Upstage.
- August 4 Sweden 15MW data center project broadens European inference demand beyond Korea.
- August 6 Backend.AI benchmarking showed 1.3-1.5x efficiency gains for enterprise inference.
What critics are saying
- FuriosaAI reported 5.74 billion won revenue against 62.48 billion won operating loss in 2025.
- Auditor Samil PwC flagged going-concern uncertainty; financing failure before 2027 threatens survival.
- Nvidia, AMD, and Rebellions can commoditize inference; missed 2027 volume makes FuriosaAI irrelevant.
What makes FuriosaAI unique
- RNGD uses 180-watt cards with 48GB HBM3 for air-cooled inference deployments.
- Broadcom partnership, announced May 28, 2026, extends RNGD into networking and packaging.
- Samsung SDS's July 20 NPUaaS and Equinix Lisbon validate commercial, multi-region deployment.
Help us improve and share your feedback! Did you find this helpful?
Benefits
- Hybrid Work Options