Edge AI Engineer for Real-Time ML on Embedded Devices
Posted Updated
Description
Placements24 in Rustenburg, North West, seeks a Machine Learning Engineer with edge AI expertise to design, optimize, and deploy ML models on resource-constrained edge devices. On-site role focusing on efficient inference and hardware-aware optimization.
You will implement ML pipelines, collaborate with hardware teams, and extend embedded ML in C/C++ across microcontrollers and embedded processors, using edge frameworks and hardware targets.
Develop and optimize machine learning models for deployment on edge devices (e.g., microcontrollers, embedded processors). Implement efficient ML inference pipelines for real-time applications. Collaborate with hardware engineers to understand device constraints and optimize model performance accordingly. Quantize and prune models to reduce memory footprint and computational requirements. Develop and maintain C/C++ code for embedded ML applications. Utilize frameworks like TensorFlow Lite, PyTorch Mobile, or similar for edge deployment. Test and validate ML models on target hardware to ensure accuracy and performance. Troubleshoot and debug issues related to model deployment and performance on edge devices. Contribute to the design of new edge AI hardware and software architectures. Bachelor's or Master's degree in Computer Engineering, Electrical Engineering, Computer Science, or related field. 2+ years of experience in machine learning engineering, with a focus on edge AI or embedded systems. Proficiency in C/C++ and experience with embedded software development tools and environments. Strong understanding of ML algorithms and their application on resource-constrained devices. Experience with model optimization techniques (quantization, pruning, knowledge distillation). Familiarity with edge ML frameworks (e.g., TensorFlow Lite, MicroPython, ONNX Runtime). Experience with hardware platforms like Raspberry Pi, NVIDIA Jetson, or similar microcontrollers. Competitive contract rate Innovative edge AI projects Hands-on embedded technologies Exposure to diverse hardware platforms Collaborative Rustenburg facilitySkills
Sign in to read and join the discussion.