Embedded AI Software Engineer

About the Role

We are looking for an Embedded AI SW Engineer to design and deploy AI-enabled embedded systems around a multi-vendor AI chiplet platform. In this role, you will bridge hardware, low-level AI accelerators, and complex software stacks to enable sustainable, safety- and security-aware AI pipelines in embedded automotive or industrial environments.

Key Responsibilities

• Execute embedded deployment of neural network models, including model slicing, retraining (or fine-tuning) strategies, and quantization-aware deployment.
• Deployment and tuning of AI models on embedded targets, including memory, bandwidth, and power-aware partitioning.
• Integrate selected AI accelerator toolchains into the internal tool environment, enabling end-to-end model development, optimization, and deployment.
• Extend and evolve AI Glue (OpenVX glue-code generator) to automate mapping of AI graphs and kernels to heterogeneous chiplets and backends.
• Integrate and visualize AI pipeline behavior and performance via PRISM-based or similar visualization tools.
• Develop and optimize OpenVX accelerator backends and kernels for the Bosch chiplet project, including computer vision pipelines and different AI workloads.
• Implement and tune OpenCL and Vulkan kernels for sensor and image processing pipelines (image acquisition and pre-processing) on GPU and hardware accelerators.
• Collaborate with hardware teams to define and refine chiplet-specific APIs, memory models, and communication protocols (e.g., UCIe, host-side drivers).
• Ensure sensor-to-AI data flows are optimized for bandwidth, latency, and determinism, including safety-critical constraints where applicable.

Required Qualifications

• 4-7 years of experience in embedded software engineering, with a strong focus on AI, computer vision, or heterogeneous computing platforms.
• Strong proficiency in C++ and embedded systems programming, with experience in real-time or safety-critical environments.
• Expertise in OpenVX, OpenCL, and/or GPU compute frameworks (e.g., Vulkan), especially for computer vision and/or AI pipelines.
• Good understanding of AI chiplets, heterogeneous acceleration, and high-speed interconnects (e.g., UCIe) and host-side drivers.
• Experience with AI model deployment on embedded targets, including model partitioning, slicing, quantization, and toolchain integration (e.g., TensorRT, ONNX-Runtime, vendor-specific stacks).
• Familiarity with AI accelerator toolchains and neural network models to AI chiplet mapping.
• Knowledge of OpenVX glue-code generators / AI glue frameworks and experience in extending such code generators is a strong plus.
• Understanding of safety- and security-critical requirements (e.g., ISO 26262, AUTOSAR, or industrial safety standards) and how to monitor AI workloads in such environments.
• Good written and verbal communication skills, with the ability to document architecture, APIs, and integration guidelines.