Data Scientist

Data Scientist Irving,Texas 3+ months contract Job summary Primary Skills: Machine Learning, Python, Data science Gather requirements from the business users on the deployment of various Machine Learning models as part of marketing analytics project. Analyze consumers data and create machine learning models to provide evidence- based insights for target-based recommendations to improve customer experience. Create model validation process to measure the performance of existing deployments and track impact for current and future deployments. Required Skills Technical Skills- ,Data Science Domain Skills- 5.Nice to have skills Techincal Skills- ,3NF data modeling,Python,PL/SQL,Machine Learning Roles & Responsibilities Implement end-to-end ML pipelines on Big Data using complete Hadoop solutions along wit PySpark, Scala, RDDs, DataFrames and DataSet APIs. Implement spark in performing ETL using Spark Core SparkSQL and Realtime data processing using Spark Streaming. Process the HDFS data, create external tables using Hive and develop scripts to ingest and repair tables that can be reused across the project. Developing shell scripts for validation of source files and data loading procedures, writing multiple scripts for pre-processing the files. Performance tuning on Spark Applications for setting the right Batch Interval time, correct level of Parallelism, memory tuning. Implement Proof of Concepts on Hadoop stack and different big data analytic tools, Migration from different databases. Develop complex SQL and Hive Queries for backend database analysis, which includes complex datatypes. Generate different types of reports using HiveQL for business to analyze the data feed from sources.