Software Engineer (On-Device AI)

Build the local compute layer for personal AI: runtime, SDK, GPU offload, developer tools, and product prototypes for WiCi One.

Work across systems, AI infrastructure, networking, and product engineering to make nearby GPU compute feel fast, reliable, and easy to use from phones, laptops, speakers, robots, and other devices.

Design and implement low-latency paths for AI workloads: voice agents, multimodal assistants, local copilots, smart-space intelligence, robotics interfaces, and developer demos.

Own hard technical problems end to end, from architecture and implementation to debugging, profiling, documentation, and launch.

Work closely with hardware, product, and research to turn WiCi’s wireless GPU architecture into developer-facing experiences people can actually build on.

Strong engineering background in systems, AI infrastructure, GPU/runtime work, networking, SDKs, ML inference, developer tools, or hardware-adjacent software.

Excellent coding ability in one or more of Linux kernel, wireless driver, CUDA, or similar systems/product engineering stacks.

Comfort debugging across layers: application, runtime, model serving, network, OS, hardware, and developer experience.

Strong product instinct. You should care not only whether the system works, but whether a builder can understand it, trust it, and ship with it.

Evidence of serious technical work: shipped products, research systems, open-source projects, startup engineering, infra work, hardware/software prototypes, or demos with real users.

Genuine interest in local AI, personal computing, low-latency interaction, privacy-preserving systems, and the future of devices with nearby compute. and comfort working across time zones.