Edge AI Engineer
Core
Design, develop, and optimize AI/ML models for deployment on resource-constrained edge devices, implementing efficient inference engines and real-time data processing pipelines.
Role type
Edge AI Engineer
Builds
Robust AI applications for edge devices (microcontrollers, specialized AI accelerators)
Domain
Embedded systems, Edge computing, Machine Learning
Deliverable
production ML models
Required skills
Python, C++, Deep learning frameworks (TensorFlow Lite, PyTorch Mobile, HailoRT), Neural network architectures, Model optimization (quantization, pruning, knowledge distillation), Edge computing platforms (NVIDIA Jetson, Google Coral, ASICs), Real-time operating systems (RTOS)
Preferred skills
Embedded software development
Technologies
TensorFlow Lite, PyTorch Mobile, HailoRT, NVIDIA Jetson, Google Coral, RTOS
Responsibilities
Design and optimize AI/ML models for edge devices; Implement inference engines and data processing pipelines; Collaborate with hardware engineers on platform selection; Optimize model performance for power, latency, and memory; Develop MLOps strategies for edge AI; Conduct performance benchmarking and validation; Document designs and architectures.
Seniority
Mid-level, hands-on IC
