About

Mannu Jha is an Applied Machine Learning and Computer Vision Engineer with 3.6 years of relevant experience in the Video Analytics Domain. He is skilled in coding languages such as C, C++, Python, and SQL, and has expertise in Image Processing libraries like OpenCV and FastCV. Mannu has experience working with various Neural Network architectures such as VGG-16, ResNet, DenseNet, YOLO, Inception, MaskRCNN, Fast-RCNN, and Detectron2. He has also worked on porting and optimizing code for GPU using OpenCL. Mannu has sound knowledge of Pose Estimation techniques such as OpenPose and BlazePose. He has worked on Object Detection, Classification, and Segmentation. He has experience deploying models using Flask and MLflow. Mannu has also worked on event streaming platforms like Kafka and NATS jetstream. Currently, Mannu is working as a Senior Engineer - Deep Learning at Tata Elxsi. He has worked on faulty Rail track open/close tip detection using traditional Image Processing and Segmentation-based solutions. He is currently working on the Point Cloud Library to detect and classify objects for self-driving cars. Mannu has also worked as a Blog Contributor at Medium and as a Kaggle Contributor. He holds a Bachelor's degree in Electronics and Communication from Gujarat Technological University, Ahmedabad, and has completed a Professional Training course in Embedded Systems from Vector India. Mannu's technical expertise includes Deep Learning, Image Processing, Computer Vision, AI, Object Detection, ResNet, SQL, OpenCV, Python, ML, Flask, Neural Networks, Kafka, TensorFlow, Keras, Docker, Pandas, MySQL, DevOps, Azure, Integration, Mobile, and Senior Software Engineer. With 4.28 years of relevant experience, Mannu is a skilled and experienced professional who can contribute to any team in the field of Machine Learning and Computer Vision.