Job Details

• Responsible for the model development from ideation to design, development, deployment and maintenance end to end
• Responsible for the data extraction required for modeling from different type of data sources like AWS, Hadoop, RDBMS, etc.
• Responsible for model deployment into production for system integration
• Responsible for automating the model refresh on a regular basis
• Responsible for monitoring the model performance in production.
• Responsible for troubleshooting performance issue in production.
• Responsible for improving the model performance ongoing in production
• Manage and analyze available data set for model development
• Apply feature engineering and feature reduction to improve model quality
• Has to be flexible to leverage different open source or vendor product
• Be able to operate with minimal supervision.
• Generate/validate performance result according to the business metrics required
• Develop/support data feed between the client and the ML env.
• Develop/maintain customer profile aggregation.
• Lead peer review, QBRs participation, mentoring other team members.

• 7-9 Years of experience in total with Minimum of 5 years of related experience in Model development
• Model development: Python scikit, Spark mllib, Google tensorflow, H2O, AWS ML, Azure ML, IBM Watson
• Model data preparation: SQL, Hadoop, AWS, Azure, Google cloud
• Feature engineering and feature reduction techniques
• Model deployment and management: Python, Java
• Model performance monitoring: SQL
• Working knowledge of Hadoop and other big data technologies

Reference ID - GH/IT/JC//14062018//76351/Data Scientist