Data Scientist - PayU Finance India Private Limited

About PayU
PayU, a leading payment and Fintech company in 50+ high-growth markets throughout Asia, Central and Eastern Europe, Latin America, the Middle East and Africa, part of Prosus group, one of the largest technology investors in the world is redefining the way people buy and sell online for our 300.000+ merchants and millions of consumers. 
As a leading online payment service provider, we deploy more than 400 payment methods and PCI-certified platforms to process approximately 6 million payments every single day. 
Thinking of becoming a PayUneer and you are curious to know more about us? Read more about the life in PayU here 
Job Description:
We are looking for a senior data scientist in the PayU Finance intelligence team who will be primarily responsible for modeling complex 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 various data sources and analytics to look at the problems by applying data mining techniques, doing statistical analysis, validating your findings using an experimental and iterative approach, and building high-quality prediction systems integrated with our services. You will need 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-time decision systems.Identify what data is available and relevant, including internal and external data sources, leveraging new data collection processes 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 performance
Skills and Qualifications:Bachelors in mathematics, statistics or computer science or a related field; Masters or PHD degree preferred.2+ 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 potentially large datasets.Proficiency in statistical analysis, quantitative analytics, forecasting/predictive analytics, multivariate testing, and optimization algorithms.Proficient in deep learning (CNN, RNN, LSTM, attention models, etc.), machine learning (SVM, GLM, boosting, random forest), graph models and reinforcement learning Experience 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 with original solutions to mathematical issues.Tracks and manages changes in a model and related development scripts (Version Control). Maintain changes and modifications over time.Should have experience in all aspects of data science life cycle - Manage, Develop, Deploy, Monitor, track modelsUnderstanding of Cloud Platforms (AWS) and ability to use them for developing, training and testing models