You will be responsible for:
• Apply your expertise in statistics, data analysis, and machine learning to develop data-automated systems and algorithms to improve performance for the online retailer world.
• Create predictive user-behavior models, recommendation and ranking systems, anomaly detection mechanisms, real-time segmentation streams and more, by converting massive, noisy data sets into significant outputs.
• Dig into the latest big data technologies to develop distributed, high-throughput, real-time products.
• Make independent decisions on how to solve specific problems based on raw datasets.
• Stay connected with the business domains and develop predictive models to support business decisions.
Requirements:
• 2+ years experience in design, coding, and optimizing predictive and clustering models.
• 1+ years experience writing production Python code including experience with Numpy, Scipy, NLTK, Pandas, PIL
• Knowledge of SQL and NoSQL.
• Strong background in statistics.
• Exp. with few of the following models: Logistic Regression, Collaborative Filtering, SVM, K-armed bandits, Markov Models, Random Forests, Game Theory.
• Dynamic, agile and comfortable with the whole data stack.
• Capable of adjusting quickly to changing requirements, and can deliver rapid and correct solutions.
• Able to communicate the results of analyses in a clear and effective manner.
Advantages:
• Experience with the Ad-tech or E-commerce world
• Scala, R, and Octave.
• Experience using distributed computing ecosystems. Experience with the Hadoop, Spark, Kafka, and HBase is preferred.