AI Product, Senior Engineer (VLM & Computer Vision)

Nabeh, a subsidiary of Master Works, delivers AI-powered solutions that help organizations automate operations, boost efficiency, and drive innovation. Its expertise spans computer vision, LLM applications, speech-to-text, data intelligence, and low-code AI solutions.

Nabeh is looking for an AI Product Engineer (Computer Vision & VLM) to develop, integrate, optimize, and deploy Vision Language Models (VLMs), computer vision solutions, and real-time video analytics capabilities across its Baseer product portfolio. The role focuses on transforming live camera feeds, recorded videos, and images into actionable insights, structured events, and AI-driven workflows for enterprise applications.

Computer Vision Development

•  Develop and integrate computer vision models for object detection, tracking, classification, segmentation, and visual event recognition.

•  Implement solutions using YOLO, OpenCV, PyTorch, and other modern computer vision frameworks.

•  Design video analytics pipelines for multi-camera environments.

•  Build use cases involving people counting, occupancy, object tracking, activity recognition, safety compliance, and operational monitoring.

•  Implement video analytics workflows involving regions of interest, event triggers, and configurable business rules.

•  Evaluate accuracy under real-world conditions, including variable lighting, occlusions, camera angles, and environmental changes.

Vision Language Models & Multimodal AI

•  Integrate VLMs to analyze images, video frames, and visual events using natural-language instructions.

•  Develop visual question answering, image understanding, scene description, and visual reasoning capabilities.

•  Combine traditional computer vision models with VLMs to improve contextual understanding and event interpretation.

•  Build video summarization, semantic video search, and natural-language querying capabilities.

•  Develop multimodal workflows combining visual intelligence with LLMs, RAG, and AI agents.

•  Evaluate VLM performance, accuracy, hallucinations, latency, and inference cost.

Real-Time Video Processing

•  Design and implement video ingestion and processing pipelines using RTSP, GStreamer, FFmpeg, or equivalent technologies.

•  Build scalable architectures for processing multiple concurrent video streams.

•  Implement frame sampling, batching, inference scheduling, stream recovery, and efficient resource utilization.

•  Optimize video processing performance to meet target FPS, latency, and infrastructure requirements.

•  Transform video events into structured metadata, alerts, searchable information, and business insights.

•  Work with both live camera feeds and recorded video sources.

AI Model Deployment & Optimization

•  Deploy and optimize computer vision and VLM models on cloud, on-premises, and edge infrastructure.

•  Work with NVIDIA GPUs and edge AI platforms such as NVIDIA Jetson.

•  Support inference optimization using TensorRT, ONNX Runtime, or equivalent frameworks.

•  Explore deployment and optimization on Qualcomm Cloud AI accelerators where supported.

•  Implement model benchmarking, performance monitoring, and resource utilization tracking.

•  Integrate models with video management systems and enterprise applications.

Product Engineering

•  Develop backend APIs and services to integrate AI models into web-based products and dashboards.

•  Build reusable computer vision pipelines and configurable analytics components.

•  Collaborate with product managers and UI/UX engineers to deliver complete product features.

•  Create configurable use cases rather than hardcoded customer-specific implementations.

•  Contribute to product architecture, technical documentation, automated testing, and release processes.

•  Own assigned features from development through deployment and ongoing optimization.

REQUIRED TECHNICAL SKILLS/EXPERINCE

•  3–6 years of relevant experience.

•  Strong Python programming experience.

•  Hands-on experience with OpenCV, PyTorch, and computer vision models.

•  Practical experience with object detection and tracking models, including YOLO.

•  Experience processing images and video from cameras or recorded sources.

•  Strong understanding of image preprocessing, inference pipelines, and model performance metrics.

•  Familiarity with VLMs such as Qwen-VL, LLaVA, or equivalent.

•  Experience developing backend APIs using FastAPI or similar frameworks.

•  Familiarity with Linux, Docker, Git, and AI deployment workflows.

•  Ability to troubleshoot model accuracy, performance, and video pipeline issues.

• Fluency in both Arabic and English, with strong verbal and written communication skills.

PREFERRED QUALIFICATIONS

• Experience with real-time multi-camera video analytics platforms.

•  Knowledge of RTSP, GStreamer, FFmpeg, and video codecs such as H.264/H.265.

•  Experience with tracking frameworks such as ByteTrack or DeepSORT.

•  Experience with segmentation, pose estimation, OCR, and action recognition.

•  Familiarity with video-language models and temporal video understanding.

•  Experience with ONNX, TensorRT, model quantization, and inference acceleration.

•  Experience deploying AI workloads on NVIDIA Jetson, NVIDIA GPUs, or Qualcomm AI platforms.

•  Knowledge of video management systems, camera integration, and edge computing.

•  Experience with Kubernetes and distributed inference architectures.

•  Experience developing AI solutions for transportation, aviation, surveillance, industrial inspection, or smart cities.