Greater Delhi Area
AI Automation Engineer and Computer Vision Engineer with a B.Tech degree from Delhi Technological University (DTU), passionate about building real-world AI systems across computer vision, agentic workflows, and retrieval-augmented generation (RAG). I enjoy building practical AI applications that solve real problems, including multi-camera vision systems, intelligent video analytics pipelines, local AI assistants, document Q&A systems, and agentic workflows powered by LLMs. Previously worked as a Computer Vision Engineer at NAYAN AI, where I developed and deployed AI systems involving object detection, person search, CCTV analytics, RTSP-based pipelines, and edge inference using models such as YOLO and ArcFace. My recent work has been focused on: • AI Agents & Tool-Use Systems • RAG Pipelines & Document AI • Local AI using Ollama & Open-Source LLMs • Workflow Automation • Multimodal AI Systems • Computer Vision & Video Analytics I enjoy working at the intersection of AI engineering, automation, and practical product development, with a strong focus on building deployable and scalable systems. Always interested in building impactful AI solutions, collaborating on innovative ideas, and exploring practical applications of artificial intelligence.
I developed a machine learning model that groups images with similar faces together using deep learning-based face detection, feature extraction, and clustering algorithms. The project involved creating a feature extraction mechanism and applying clustering algorithms to effectively cluster images based on facial similarities. A custom face dataset was created for this project using YOLOv8, a deep learning object detection model. Different PyTorch models were analyzed for feature extraction like ResNet18, VGG16, DenseNet161.
In charge of gathering and analysing data from sensors and chemical tests performed on the rover.