Senior Computer Vision Specialist / AI Engineer

As a highly experienced Computer Vision Specialist / AI Engineer, you will lead the design, development, and deployment of computer vision and AI-based systems. Your responsibilities will include architecting and implementing advanced vision-based algorithms and deep learning models, delivering real-time solutions for various applications such as facial recognition, motion detection, object detection, number plate recognition (ANPR), footfall counting, gender and age detection, behavioral analysis, and emotion recognition. Additionally, you will optimize AI/ML models for deployment on edge devices, cloud, or hybrid environments using tools like TensorRT, OpenVINO, or ONNX. Collaboration with hardware and software teams, conducting performance benchmarking, testing, and continuous improvement, as well as providing technical leadership within the team will be key aspects of your role. Key Responsibilities: - Lead the design, development, and deployment of computer vision and AI-based systems. - Architect and implement advanced vision-based algorithms and deep learning models. - Deliver real-time solutions for: - Facial Recognition (1:1 and 1:N) - Motion and Intrusion Detection - Object and Vehicle Detection & Tracking - Automatic Number Plate Recognition (ANPR) - Footfall Counting - Demographic Analytics (Age, Gender) - Behavioral & Emotion Analysis - Optimize AI/ML models for deployment on edge devices, cloud, or hybrid environments using TensorRT, OpenVINO, ONNX, or similar. - Collaborate with hardware and software teams to ensure end-to-end system performance. - Conduct performance benchmarking, testing, and continuous improvement. - Document all phases of development and provide technical leadership within the team. Required Skills & Experience: - Minimum 6 years of hands-on experience in Computer Vision, Machine Learning, and Deep Learning. - Successfully completed at least 10 deployed/commercial projects in computer vision. - Proficiency in libraries and frameworks: OpenCV, TensorFlow, PyTorch, Keras, YOLO, MediaPipe, Dlib. - Deep knowledge of: - CNN, RNN, Transformer-based architectures - Object detection (YOLO, SSD, Faster R-CNN) - Face detection and recognition (FaceNet, ArcFace) - Behavior and sentiment analysis using video feeds - Experience in model optimization and deployment using TensorRT, ONNX, OpenVINO, etc. - Experience deploying on NVIDIA Jetson, Coral Edge TPU, CPU/GPU inference platforms, etc. - Strong Python and C++ programming skills. - Hands-on with deployment on cloud platforms (AWS, Azure, GCP) and containerization (Docker, Kubernetes). Relocation Requirement: This position is based in Maharashtra. Only candidates willing to relocate and work on-site will be considered. Compensation: Competitive salary with performance-based bonuses. Relocation assistance and accommodation support (if required).,