Pyspark Developer

Key Responsibilities

• Work with leading banks' Risk Management teams on projects related to consumer and wholesale banking risk models.
• Develop, fine-tune, and implement programs using PySpark, Python, Scala on Big Data/Hadoop platforms.
• Enhance and deploy machine learning models based on business requirements.
• Participate in feature engineering, model training, scoring, and retraining processes.
• Architect and automate data pipelines and model jobs for production deployment.
• Conduct sophisticated statistical analysis using bureau/vendor data, customer performance data, and macroeconomic data.
• Implement code validation, model deployment, and system integration using distributed systems like Hadoop, Spark, and MapReduce.
• Act as a liaison between business and IT to communicate requirements, constraints, and strategy.
• Stay updated with regulatory requirements and ensure compliance in all implementations.