Artificial Intelligence Engineer

AFCO - Food Company; Dammam; On-site; SAR 300,000 - 460,000; Full time

Job summary

AFCO - Food Company seeks a Senior AI & Computer Vision Engineer to lead AI-powered CCTV and video analytics initiatives. You will develop, optimize, and deploy real-time CV systems that analyze CCTV feeds and extract actionable insights for business operations.

The role requires 5+ years in AI and CV, strong Python and deep learning skills, and experience with OpenCV, PyTorch/TensorFlow, and YOLO. Collaboration with DevOps, data teams, and stakeholders is essential.

Qualifications

• Bachelor's or master's in CS/AI/ML/CE required.
• 5+ years in AI, CV, ML, or video analytics.
• Strong Python programming and real-time CV experience.
• Experience with CCTV/video streams and standard CV tools.

Responsibilities

• Develop and deploy AI-powered CCTV and video analytics solutions.
• Process multiple live CCTV streams with RTSP and protocols.
• Optimize models for real-time inference on GPU/edge.
• Integrate AI with CCTV hardware, NVR/DVR, and VMS.
• Collaborate with software, DevOps, data teams and stakeholders.
• Stay updated on CV, Video AI, and multimodal AI trends.

Skills

Python

Computer Vision

Deep Learning

Video Analytics

Object Detection

Real-time Processing

Model Optimization

GPU Inference

Troubleshooting

Team Collaboration

Education

Bachelor's or Master's in CS/AI/ML/CE

Tools

OpenCV

PyTorch

TensorFlow

YOLO

CUDA

TensorRT

DeepStream

Linux

Docker

REST APIs

Job description

About the Role

We are looking for an experienced Senior AI & Computer Vision Engineer to join our technology team and lead the development of AI-powered CCTV and video analytics solutions.

The successful candidate will be responsible for developing, optimizing, and deploying real-time computer vision systems that analyze CCTV footage and generate actionable insights for business and operational use cases.

Key Responsibilities

• Develop and deploy AI-powered CCTV and video analytics solutions.
• Develop real-time video analytics using Python, OpenCV, PyTorch/TensorFlow, YOLO, and related technologies.
• Process and analyze multiple live CCTV streams using RTSP and other video streaming protocols.
• Integrate AI solutions with CCTV cameras, NVR/DVR systems, VMS platforms, and APIs.
• Optimize AI models for real-time inference, GPU/CPU performance, and edge deployment.
• Work with technologies such as NVIDIA CUDA, TensorRT, and DeepStream where applicable.
• Develop and deploy solutions for use cases such as people counting, vehicle detection, occupancy monitoring, queue analytics, intrusion detection, safety compliance, and abnormal activity detection.
• Continuously monitor, evaluate, and improve model accuracy and system performance.
• Collaborate with software engineers, DevOps, data teams, and business stakeholders to take AI solutions from development to production.
• Stay updated with emerging technologies in Computer Vision, Video AI, Generative AI, and multimodal AI.

Required Skills & Experience

• 5+ years of relevant experience in AI, Computer Vision, Machine Learning, or Video Analytics.
• Bachelor's or master's degree in computer science, AI, Machine Learning, Computer Engineering, or a related field.
• Strong programming skills in Python.
• Strong hands-on experience with Computer Vision and Deep Learning.
• Experience with OpenCV, YOLO, PyTorch and/or TensorFlow.
• Strong understanding of object detection, tracking, segmentation, classification, and real-time video processing.
• Practical experience working with CCTV/video streams.
• Knowledge of RTSP, ONVIF, NVR/DVR, and VMS integration is highly desirable.
• Experience with GPU-based AI inference, CUDA, TensorRT, or NVIDIA DeepStream is an advantage.
• Experience with Linux, Docker, Git, REST APIs, and production AI deployment.
• Strong troubleshooting, analytical, and problem-solving skills.

Preferred Experience

Candidates with experience in CCTV analytics, video surveillance, retail, QSR/F&B, smart buildings, logistics, IoT, security systems, or other real-time video intelligence applications will be highly preferred.

Experience with ANPR/ALPR, facial recognition, behavioral analytics, Vision-Language Models (VLMs), or multimodal AI will be an added advantage.