Systems Software Engineer, NPU Management Interface
FuriosaAI · Seoul, South Korea
Infrastructureonsite
At a glance
Highlights
- Design NPU management firmware enabling host and BMC communication.
- Build health, power, and thermal telemetry for AI inference hardware.
- Ship real-world silicon with RNGD now in mass production.
Ideal candidate
Embedded firmware engineer energized by AI hardware and spec-driven design who loves low-level debugging and bringing complex, rack-scale systems from bring-up to production.
Requirements
- Strong proficiency in embedded C or C++
- Experience with firmware development for NPU/accelerator, GPU, or SoC
- Understanding of management protocols including MCTP and PLDM
- Experience with low-level interfaces: SMBus/I2C, I3C, SPI, PCIe
- Ability to interpret complex protocol specifications into robust implementations
- Familiarity with device telemetry, sensor frameworks, and health monitoring
- Experience with system-level debugging using logic/protocol analyzers
- Knowledge of embedded systems, bare-metal or RTOS environments
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