We are looking for a senior data scientist in the PayU intelligence team who will be primarily responsible for modelingcomplex problems, discovering insights, and identifying opportunities through the use of statistical, algorithmic, mining,and visualization techniques. Your primary focus will be to propose innovative ways utilizing graph databases and analyticsto look at the problems by applying data mining techniques, doing statistical analysis, validating your findings using anexperimental and iterative approach, and building high-quality prediction systems integrated with our services. You willneed strong business understanding, analytical and problem-solving skills, and programming knowledge.
Responsibilities
Design experiments, test hypotheses, and build models utilizing the traditional datasets and graph data.Apply advanced statistical and predictive modeling techniques to build, maintain, and improve on multiple real-timedecision systems.Identify what data is available and relevant, including internal and external data sources, leveraging new data collectionprocesses such as geo-location or social mediaUtilize patterns and variations in the volume, speed and other characteristics of data for predictive analysis.Define the preprocessing or feature engineering to be done on a given dataset, data augmentation pipelines, trainingmodels and tuning their hyperparameters, analyzing the errors of the model and designing strategies to overcome themSelecting features, building and optimizing classifiers using machine learning techniquesExtending company’s data with third party sources of information when neededCreating automated anomaly detection systems and constant tracking of its performanceSkills And Qualifications
Bachelors in mathematics, statistics or computer science or a related field; Masters or PHD degree preferred.5+ years of relevant quantitative and qualitative research and analytics experience.Extensive knowledge of statistical techniques.Ability to come up with solutions to loosely defined business problems by leveraging pattern detection over potentiallylarge datasets.Proficiency in statistical analysis, quantitative analytics, forecasting/predictive analytics, multivariate testing, andoptimization algorithms.Proficient in deep learning (CNN, RNN, LSTM, attention models, etc.), machine learning (SVM, GLM, boosting, randomforest), graph models and reinforcement learningExperience with open source tools for deep learning and machine learning technology such as Keras, tensorflow, pytorch,scikit-learn, pandas, etc.Strong programming skills (Hadoop MapReduce or other big data frameworks, Java, Python), statistical modeling (R,Python, SAS), query languages such as SQL, Hive, PigFamiliarity with basic principles of distributed computing and distributed databases.Demonstrable ability to quickly understand new concepts - all the way down to the theorems - and to come out withoriginal solutions to mathematical issues.
