Senior Artificial Intelligence Engineer - CCTV Video Analytics

Overview

We are seeking a seasoned Senior AI & Computer Vision Engineer specializing in CCTV analytics to join our advanced technology department in Dammam, Saudi Arabia. This full-time role involves leading the creation and deployment of AI-driven real-time video analytics systems that process CCTV footage to provide actionable insights for operational use.

Responsibilities

• Develop AI-based CCTV and video analytics applications focusing on object detection, tracking, classification, segmentation, and event/behavior recognition.
• Implement real-time analytics pipelines using Python with frameworks such as OpenCV, PyTorch, TensorFlow, and YOLO.
• Handle multiple live CCTV video streams via RTSP and other streaming protocols for continuous analysis.
• Integrate AI models with CCTV hardware including NVR/DVR systems, VMS platforms, and associated APIs.
• Optimize algorithms for high-performance inference on GPUs and CPUs, including edge device deployments.
• Utilize NVIDIA technologies such as CUDA, TensorRT, and DeepStream where applicable to boost efficiency.
• Create solutions tackling challenges like crowd counting, vehicle detection, occupancy monitoring, queue management, intrusion detection, safety compliance, and abnormal activity detection.
• Continuously assess and enhance model precision and system responsiveness.
• Collaborate with cross-functional teams including software engineers, DevOps, data analytics, and business units to deploy AI solutions into production environments.
• Stay abreast of innovations in Computer Vision, Video AI, Generative AI, and multimodal AI.

Qualifications and Skills

• At least 5 years of professional experience in Artificial Intelligence, Computer Vision, Machine Learning, or Video Analytics development.
• A bachelor's or master's degree in Computer Science, AI, Machine Learning, Computer Engineering, or closely related disciplines.
• Proficient programming skills in Python with hands-on expertise in Computer Vision and deep learning technologies.
• Experience using OpenCV, YOLO, PyTorch, and/or TensorFlow frameworks.
• Thorough understanding of techniques for object detection, tracking, image segmentation, classification, and processing real-time video streams.
• Practical knowledge of working with CCTV and video streams, including familiarity with RTSP, ONVIF, NVR/DVR, and video management system integration.
• Experience in GPU-accelerated AI inference, and tools like CUDA, TensorRT, or NVIDIA DeepStream is a plus.
• Competence in Linux environments, containerization with Docker, version control using Git, RESTful API development, and deploying AI in production systems.
• Excellent analytical, debugging, and problem-solving abilities.

Desirable Industry Experience

Exposure to sectors leveraging CCTV analytics such as retail, quick service restaurants, food and beverage, smart building systems, logistics, IoT, security, or other domains requiring real-time video intelligence will be valued.

Knowledge in advanced domains like ANPR/ALPR, facial recognition, behavioral analytics, Vision-Language Models, or multimodal AI is considered advantageous.