Lead Embedded AI Software Engineer

About the role

We are looking for a Lead Embedded AI Software Engineer to design and deploy AI‑enabled embedded systems on a multi‑vendor AI chiplet platform. You will bridge hardware, low‑level AI accelerators, and complex software stacks to create sustainable, safety‑ and security‑aware AI pipelines for automotive or industrial applications.

Key responsibilities

• Define the embedded AI software architecture for multi‑vendor AI chiplet platforms.
• Drive host‑side CPU orchestration and code optimizations.
• Design and implement efficient hardware‑software interfaces (HSI) via UCIe‑based communication, drivers, and access‑management layers.
• Implement and optimise AI inference pipelines using C++ and OpenVX, targeting performance, latency, and resource constraints.
• Develop and maintain safety‑ and security‑monitoring components for AI workloads (health checks, secure execution, anomaly detection).
• Consult on model partitioning, slicing, retraining or fine‑tuning, and quantisation‑aware deployment.
• Lead initial deployment and tuning of AI models on embedded targets, considering memory, bandwidth, and power constraints.

Required profile

• Strong proficiency in C++ and embedded systems programming, with experience in real‑time or safety‑critical environments.
• Deep expertise in OpenVX, OpenCL, and/or GPU compute frameworks such as Vulkan, especially for computer‑vision or AI pipelines.
• Solid understanding of AI chiplets, heterogeneous acceleration, high‑speed interconnects (e.g., UCIe), and host‑side drivers.
• Familiarity with AI accelerator toolchains and neural‑network model mapping to AI chiplets.

Required skills

• C++
• Embedded systems programming
• OpenVX
• OpenCL
• Vulkan
• UCIe interconnect
• AI chiplet platforms
• Real‑time and safety‑critical development
• GPU compute frameworks
• AI accelerator toolchains
• Neural‑network model mapping