Embedded AI Software Engineer Mid-Level

About the role

Bosch Group is seeking a mid‑level Embedded AI Software Engineer to design and deploy AI‑enabled embedded systems on a multi‑vendor AI chiplet platform for automotive and industrial applications.

Key responsibilities

• Execute embedded deployment of neural network models, including model slicing, retraining/fine‑tuning, and quantization‑aware deployment.
• Deploy and tune AI models on embedded targets, optimizing for memory, bandwidth, and power constraints.
• Integrate AI accelerator toolchains into Bosch’s internal development environment.
• Extend the AI Glue (OpenVX glue‑code generator) to automate mapping of AI graphs and kernels to heterogeneous chiplets and back‑ends.
• Integrate and visualize AI pipeline behavior and performance using PRISM‑based or similar tools.
• Develop and optimise OpenVX accelerator back‑ends and kernels for Bosch chiplet projects, covering computer‑vision pipelines and diverse AI workloads.
• Implement and tune 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 are optimised for bandwidth, latency, determinism, and safety‑critical constraints where applicable.

Required profile

• 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 development.
• Hands‑on experience with AI accelerators, toolchains, and deployment on embedded targets.
• Familiarity with safety‑critical development constraints is a plus.

Required skills

• C++
• OpenVX
• OpenCL
• Vulkan
• AI accelerator toolchains
• Neural network model deployment and quantization‑aware training
• GPU programming
• Hardware accelerator integration
• PRISM visualization
• UCIe communication protocol
• Host‑side driver development
• Sensor data processing
• Computer‑vision pipeline development
• Heterogeneous computing