Staff Engineer
Kandou AI
Staff Engineer
Kandou AI
Provides chip-to-chip AI connectivity solutions
The responsibility of this role is to develop firmware modules and services for Kandou’s Memory fabrics products
Firmware is responsible for implementing and supporting the major differentiating features of Kandou’ products.
Basic qualification
Strong academic and technical background in Electronics & Computer engineering. At a minimum, a Bachelor’s in EE or Computer Science is required, and a Master’s is preferred.
Experience developing firmware (Bare metal/RTOS) to execute in on-chip microcontrollers/processors
Minimum 8-15 years’ experience developing firmware for Server, Storage, and/or Networking SoC products
Required experience
Hands-on experience designing and developing embedded firmware for PCIe/CXL/NVME protocols with proficiency in C (preferred) or C++, including development of C-based SDKs.
Experience with RTOS/Zephyr OS firmware development and enablement
Familiar with SoC interfaces to common IP blocks such as PCIe Controllers, NVME Controllers, DDR controllers, AMBA/AHB interfaces, on-chip memory interfaces, and other similar interfaces
Work with various cross-functional groups such as architect, other development teams, QA/validation, product management and customer teams across various sites
Preferred experience
Experience with DDR controller, storage or SSD firmware, including NVMe, PCIe, CXL or flash management concepts.
Hands-on experience with simulation or virtual platform–based development (e.g., Renode, QEMU, or similar)
Kandou AI designs and sells semiconductor connectivity hardware for AI workloads. It provides a memory fabric and CXL controllers that link processors to memory, enabling scalable, energy-efficient AI inference and training clusters built from affordable hardware. Using Copper MIMO interconnect, it reduces energy per bit and supports features like offloading AI training collectives, switchless memory for in-memory databases, and field-repairable co-packaged optics for better cooling. By targeting the data-movement bottleneck between processors and memory and offering chiplet-based fabrics and IP licensing, Kandou AI aims to make scalable AI infrastructure more accessible to hyperscalers, data centers, and system integrators.
Explore more opportunities at Kandou AI