Senior Engineer - Computer Vision, Edge Inference & Embedded Systems
Inspire Selection View all jobs
- Abu Dhabi
- Permanent
- Full-time
- Architect and implement high-performance, low-latency AI/Computer Vision systems tailored for edge deployment on NVIDIA Jetson and Orin platforms.
- Lead the selection, development, and optimization of computer vision models (e.g., object detection, segmentation, tracking) for real-time inference under constrained power and compute budgets.
- Design and manage MLOps pipelines for model training, validation, continuous integration, and deployment to edge devices, ensuring reproducibility, version control, and monitoring.
- Conduct hardware-software co-design to balance performance, power consumption, and thermal efficiency in embedded systems.
- Evaluate and recommend optimal hardware configurations, software frameworks (e.g.,TensorRT, ONNX, OpenCV), and inference engines for edge deployment.
- Mentor junior engineers on AI best practices, model architecture, and edge deployment strategies to elevate team capability.
- Define and enforce standards for model accuracy, inference speed, memory footprint, and energy efficiency across all edge AI projects.
- Collaborate with cross-functional teams (hardware, firmware, product) to integrate AI solutions into production systems with minimal latency and maximum reliability.
- Bachelor's degree in Computer Science, Electrical Engineering, Robotics, or related field; Master's or PhD preferred.
- Minimum 5 years of hands-on experience in AI/Computer Vision, with at least 3 years focused on edge AI and embedded systems.
- Deep expertise in computer vision algorithms (e.g., YOLO, EfficientDet, SegFormer, Pose Estimation) and model optimization techniques (quantization, pruning, distillation).
- Proven experience deploying AI models on NVIDIA Jetson (e.g., Jetson Nano, TX2, AGX Orin) and Orin series devices.
- Strong proficiency in MLOps tools and workflows (e.g., MLflow, Kubeflow, CI/CD for AI, model registry, containerization with Docker).
- Experience with inference engines (TensorRT, ONNX Runtime) and low-level optimization for power efficiency.
- Familiarity with real-time systems, latency-sensitive applications, and power-aware design principles.
- Demonstrated ability to lead technical design, conduct peer reviews, and guide team-wide technical standards.
- Excellent communication skills and ability to translate technical concepts for stakeholders.
- Experience with edge AI frameworks (e.g., NVIDIA DeepStream, OpenVINO, TensorFlow Lite).
- Knowledge of hardware acceleration (e.g., CUDA, Tegra, NPU) and thermal management strategies.
- Experience in autonomous systems, robotics, or smart vision systems in industrial or consumer applications.