Responsibilities: * Develop predictive models using Python & CV techniques * Optimize ML algorithms for performance & accuracy * Collaborate with cross-functional teams on project delivery
Were building some really exciting stuff in the retail AI space – smart vision, real-time insights, automation — the works. We’re looking for a Computer Vision Engineer (4+ years experience) to join our team! What you’ll be doing: Designing and training custom computer vision models tailored for real-world use cases. Containerizing (Dockerizing) applications to ensure scalability and reliability. Building systems capable of handling multiple real-time video feeds seamlessly. Architecting end-to-end solutions for the retail sector — including restaurants and supermarkets. What we’re looking for: 4+ years of hands-on experience in computer vision. Strong knowledge of deep learning frameworks (TensorFlow / PyTorch) / object detection models (Yolo, SSD, R-CNN Family). Train custom CV models that actually work in the wild (not just on benchmarks). Solid experience with Docker for deployment. Ability to design scalable architectures and optimize performance for multi-camera systems. Passion for solving problems in retail tech (customer experience, store analytics, automation). We’re a fast-moving startup you’ll have ownership, freedom to build things your way, and the chance to shape the core tech powering retail AI.
Role & responsibilities Youll lead the development and optimization of real-time video analytics pipelines for Sakshi AI. From object detection to behavioral insights, your work will power smarter decisions for retail chains across India and beyond. Preferred candidate profile Design and deploy computer vision models for object tracking, activity recognition, and anomaly detection Optimize inference pipelines for edge devices and cloud deployment Integrate CV modules with live CCTV feeds and ThinkNeurals dashboard ecosystem Collaborate with product and UX teams to translate insights into actionable alerts Conduct field testing and validation across diverse retail environments Stay updated with the latest in vision transformers, YOLO variants, and multimodal fusion Requirements 24 years of hands-on experience in computer vision and deep learning Proficiency in Python, OpenCV, PyTorch/TensorFlow Experience with real-time video processing, edge deployment, or ONNX optimization Familiarity with CCTV protocols, IP camera feeds, and video encoding formats Strong understanding of model evaluation metrics and data annotation workflows Bonus: Experience with retail analytics, pose estimation, or multi-camera setups What We Offer Ownership of core AI modules in a fast-growing product Access to real-world retail data and deployment environments Competitive compensation + ESOPs A chance to shape the future of intelligent retail infrastructure