Ganesan Vijayan

=> Possess pragmatic experience in Big Data: SQL and No SQL ETL processing using PySpark, Sqoop, Flume, Unix. => ML and DL: Data and image preprocessing, regression, classification, clustering, time serious analysis, Object identification and semantic segmentation for Texts, Images, Img-Text extraction using auto-encoders and decoders, DNN, NLP, Chat Bot implementation using Python framework and it’s libraries such as sklearn, sparkML, tensorflow, pytorch, weka, Spacy, keras, pandas, pandas profiling, numpy, seaborn, matplotlib, statsmodels, ARIMA and DL networks such as CNN, RNN, LSTM, RNTN, R-CNN, GANs. => Hands on experience in pretrained NLP architectures such as Word2Vec, BERT, ELMo, Gensim and custom architectures. => Excellent in data analytics, feature engineering, model building, model accuracy/performance tuning, model pipeline setup, deployment/scheduling, drift metrics evaluation, visualisation/reporting with python native and user defined class functions. => Good understanding of Statistics and Mathematics such as Probability and Density Distribution, Linearity, Correlation, Coeff of Variance, measures of central tendency and dispersion, Hypothesis analysis, matrices and inverse, logarithmic functions, partial derivative. => Good in Shell scripting fundamentals and Hadoop controls. => Good knowledge in CDH databases and search engines such as Hive, Impala, HBase, Kudu, ELK => Good in handling Data platform for data lake such as Cloudera, Integrated Cloudera with Cloud services such as AWS, Azure. => Certified in DataRobot for automated model development and deployment => Practicing Data Governance, Data Cataloguing => Hands-on experience in Python 3.x, Pyspark, Java and JS including fair amount of experience in Web development using Django, HTML, CSS, NodeJS for model deployment both on Client and Server sides. => Mediocre in UI/UX development of Angular 4.x and Bootstrap dashboard and templates. => Fair understanding of deployment tools such as Jenkins, AnsibleTower, AutoSys, Docker, Kebernetes, Kubeflow for CICD and data and model pipeline automation. => High level work experience in MRM process for managing ML/NLP models. => Good knowledge in handling SCM tools such as GitHub, Bitbucket, CVS and its processes. => Visualization and reporting tools such as Tableau, Panopticon, Py libs. => Inquisitiveness in generating new ideas and converting into patentable cases. => Business knowledge in various domains such as Capital Markets, Cash Management in Banking and Investments, Auto/Property/Casualty/WC Insurance, Healthcare, e-Commerce.