We are looking for an AI Engineer (Computer Vision) to design and deploy intelligent video analytics solutions using CCTV feeds. The role focuses on analyzing real-time and recorded video to extract insights such as attention levels, engagement, movement patterns, posture, and overall group behavior. You will work closely with data scientists, backend teams, and product managers to build scalable, privacy-aware AI systems.

Key Responsibilities :

- Develop and deploy computer vision models for CCTV-based video analytics

- Analyze gaze, posture, facial expressions, movement, and crowd behavior

- Build real-time and batch video processing pipelines

- Train, fine-tune, and optimize deep learning models for production

- Convert visual signals into actionable insights & dashboards

- Ensure privacy, security, and ethical AI compliance

- Improve model accuracy, latency, and scalability

- Collaborate with engineering teams for end-to-end deployment

Required Skills :

- Strong experience in Computer Vision & Deep Learning

- Proficiency in Python

- Hands-on experience with OpenCV, TensorFlow, PyTorch

- Knowledge of CNNs, object detection, tracking, pose estimation

- Experience with video analytics & CCTV data

- Understanding of model optimization and deployment

Good to Have :

- Experience with real-time video streaming (RTSP, CCTV feeds)

- Familiarity with edge AI or GPU optimization

- Exposure to education analytics or surveillance systems

- Knowledge of cloud deployment (AWS/GCP/Azure)