Principal AI SoC Runtime Software Architect
Confirmed on the employer's own hiring board on Oct 14, 2026. First seen by Alion on Aug 11, 2026.
Role Overview
We are looking for a Principal AI SoC Runtime Software Architect to own the software architecture that turns Velaura’s heterogeneous AI SoC into a coherent, high-performance execution platform.
This role will define and lead development of the end-to-end runtime spanning sensor ingest, preprocessing, AI inference, postprocessing, and delivery of results to robotics and other physical and edge AI applications. The runtime will coordinate execution and data movement across the SoC’s CPU cores, AI accelerator, vision and multimedia engines, and other embedded processors. The complete runtime must coordinate heterogeneous workloads, manage ownership, synchronization, and safe reuse of shared data buffers, minimize data movement, provide predictable low-latency execution, recover from failures, and expose cohesive APIs and observability to applications and SDK components.
The ideal candidate combines deep runtime and systems-software expertise with a strong understanding of heterogeneous compute, Linux kernel and driver interfaces, DMA and shared-memory architectures, and performance-sensitive AI or multimedia pipelines. This will be a hands-on principal architect and technical lead who directs engineers across runtime, kernel, driver, firmware, multimedia, and SDK development.