Embedded AI Software Engineer

About the role

We are seeking an Embedded AI Software Engineer to design and deploy AI‑enabled embedded systems on a multi‑vendor AI chiplet platform. You will work at the intersection of hardware, low‑level AI accelerators, and complex software stacks to create safe, secure, and efficient AI pipelines for automotive or industrial applications.

Key responsibilities

• Deploy neural network models on embedded targets, handling model slicing, fine‑tuning, and quantization‑aware deployment.
• Optimize AI models for memory, bandwidth, and power constraints on heterogeneous chiplets.
• Integrate AI accelerator toolchains into internal development environments for end‑to‑end model optimization.
• Extend the OpenVX glue‑code generator to automate mapping of AI graphs to chiplet back‑ends.
• Visualize AI pipeline performance using PRISM‑based tools or similar.
• Develop and tune OpenVX accelerator back‑ends and kernels for computer‑vision and other AI workloads.
• Implement OpenCL and Vulkan kernels for sensor and image‑processing pipelines on GPUs and hardware accelerators.
• Collaborate with hardware teams to define chiplet‑specific APIs, memory models, and communication protocols such as UCIe and host‑side drivers.
• Ensure sensor‑to‑AI data flows meet bandwidth, latency, determinism, and safety‑critical requirements.

Required profile

• Strong proficiency in C++ and embedded systems programming.
• Experience with real‑time or safety‑critical software development.
• Hands‑on knowledge of AI model deployment and optimization on embedded platforms.
• Ability to work cross‑functionally with hardware and software teams.

Required skills

• C++
• Embedded C/C++ programming
• Real‑time and safety‑critical development
• OpenVX
• OpenCL
• Vulkan
• GPU compute frameworks
• AI model deployment, quantization, fine‑tuning
• AI accelerator toolchains
• Chiplet platforms and UCIe interfaces
• PRISM visualization tools