Senior Computer Vision Engineer (Onsite, Lahore, USD Salary)

Requirements:

• 5+ years of experience in computer vision or related fields, with a proven track record of building and deploying algorithms for real-time applications (e.g., object detection, tracking, or segmentation).
• Expert proficiency in Python and computer vision/ML frameworks (e.g., OpenCV, TensorFlow, PyTorch, YOLO, Detectron2).
• Strong expertise in designing and optimizing real-time computer vision algorithms, with a focus on performance in resource-constrained environments.
• Hands-on experience with ML Ops practices, including model deployment, containerization (Docker), orchestration (Kubernetes), and CI/CD pipeline development.
• Deep understanding of machine learning and deep learning concepts, including CNNs, transformers, and optimization techniques.
• Proficiency with version control systems (e.g., Git) and software engineering best practices.
• Ability to lead complex projects, solve technical challenges, and collaborate effectively in a fast-paced, mission-driven environment.
• Experience with cloud platforms (e.g., AWS, GCP, Azure) for scalable model deployment and data processing.
• Willingness to participate in occasional on-call support for mission-critical systems.
• Experience with real-time data processing, edge computing, or IoT systems, particularly for camera-based applications.
• Familiarity with advanced computer vision techniques, such as multi-object tracking, 3D reconstruction, or low-light image processing.
• Background in traffic safety systems, smart city technologies, or autonomous vehicle perception systems.
• Expertise in managing large-scale image or video datasets, including data annotation pipelines.
• Knowledge of hardware optimization for computer vision (e.g., NVIDIA Jetson, TensorRT, or embedded systems).
• Contributions to open-source computer vision or ML Ops projects.

Responsibilities:

• Architect and build high-performance computer vision algorithms for real-time detection of traffic violations (e.g., speeding, lane violations, stop sign running) and scene analysis, ensuring accuracy and low latency.
• Develop and optimize end-to-end computer vision pipelines, from image preprocessing and model training to inference and deployment, using frameworks like OpenCV, TensorFlow, PyTorch, or ONNX.
• Lead ML Ops efforts, including model deployment, versioning, monitoring, and performance optimization, using tools like Docker, Kubernetes, and CI/CD pipelines.
• Collaborate with hardware engineers, backend developers, and data scientists to integrate computer vision models with IoT camera systems and cloud-based infrastructure.
• Design and implement scalable data preprocessing and annotation workflows to ensure high-quality datasets for training robust vision models.
• Mentor junior engineers, conduct code reviews, and enforce best practices for building maintainable, high-performance AI systems.
• Monitor and troubleshoot production systems, participating in on-call rotations to ensure reliability and performance.
• Contribute to system architecture decisions, balancing trade-offs between accuracy, speed, and resource constraints for real-time applications.