Job summary
Senior AI Product Engineer (Computer Vision & VLM) at Nabeh — a Master-Works subsidiary — based in Riyadh. The role builds and deploys vision-language models, computer vision solutions and real-time video analytics to convert camera feeds and recordings into structured insights for the Baseer product portfolio.
Key responsibilities
- Develop and integrate CV models for detection, tracking, classification, segmentation, and event recognition
- Design multi-camera video analytics pipelines and real-time processing architectures
- Integrate Vision Language Models for visual question answering and image understanding
- Build multimodal workflows combining VLMs with LLMs, RAG, and AI agents
- Optimize model inference for cloud, on-premise and edge (NVIDIA GPUs, Jetson)
- Implement video ingestion using RTSP/GStreamer/FFmpeg and handle stream recovery
- Create backend APIs and reusable analytics components for product integration
- Evaluate model accuracy, latency, hallucinations and inference cost
Requirements
- 3–6 years of relevant experience
- Strong Python programming skills
- Hands-on experience with OpenCV and PyTorch
- Practical experience with object detection and tracking (e.g., YOLO)
- Experience processing camera images and recorded video
- Familiarity with VLMs such as Qwen‑VL or LLaVA
- Experience building backend APIs (FastAPI or similar)
- Familiarity with Linux, Docker, Git and deployment workflows
- Fluent Arabic and English (written and spoken)
Skills
Source: Workable. Last checked as open: 15 Nov 2026. You apply directly with the employer.
Apply now