Job Description
- Required - Hadoop/Hive, Python, Spark
- 6+ years hands-on experience working with Big Data Platforms such as Cloudera, Hortonworks, or MapR
- Python & ML modeling experience is a plus
- Experience with using the Agile approach to deliver solutions
- Experience with handling large and complex data in Big Data Environment
- Experience with designing and developing complex data products and transformation routines
- Experience of working in financial services and risk analytics domain, a plus
- Strong record of achievement, solid analytical ability, and an entrepreneurial hands-on approach to work
- Outstanding written and verbal communication skills
Job Responsibilities
- Design, build and deploy advance analytics models aimed to improve fraud risk strategies of clients using Hadoop technology stacks and programming languages such as Hive, PySpark, Python, Spark & shell
- Design, build and deploy an anomaly detection tool to identify suspicious transaction behavior of accounts
- Develop a monitoring & alert mechanism for the anomalies using shell scripts
- Design, build and deploy self-serve reporting tool across business functions and clients
- Design complex algorithm and apply machine learning and statistical methods on large datasets for reporting, predictive and prescriptive modeling
- Develop and implement coding best practices using Hadoop/Hive, Python, and PySpark
- Collaborate with offshore and onshore team and effectively communicate status, issues, and risks daily
- Review and propose new standards for naming, describing, managing, modeling, cleansing, enriching, transforming, moving, storing, searching and delivering all data products within the enterprise
- Analyze existing and future data requirements, including data volumes, data growth, data types, latency requirements, data quality, the volatility of source systems, and analytic workload requirements
Location
Gurgaon, Haryana, India