Data Engineer (ML/AI) - Credit Risk

About the role

A Data / Machine Learning Engineer is sought to build data and machine learning infrastructure for Credit Risk systems. You will work closely with Data Scientists, Risk Policy and Engineering teams to help productionize machine learning models, maintain large-scale data pipelines and support real-time decision systems, while exploring how AI can improve model monitoring, data quality and developer productivity.

Key responsibilities

• Support deployment of machine learning models for real-time and batch risk decisions, and build and maintain model-serving and distributed inference infrastructure
• Optimize model performance, latency and system reliability
• Build and maintain data pipelines for model training and inference, and develop ETL / ELT workflows
• Work with data scientists to keep features consistent between offline and online environments
• Help build monitoring for data quality, feature drift and model performance, and troubleshoot pipeline failures
• Explore AI-assisted improvements such as pipeline diagnostics, data quality validation, model monitoring analysis and developer productivity tools

Required profile

• Bachelor's degree in Computer Science, Software Engineering, Data Engineering, Data Science, AI, Machine Learning, Computer Engineering, Statistics, Applied Mathematics or a related field
• Minimum 3 years of experience in Data Engineering, Machine Learning Engineering or a related field
• Experience building data pipelines or ML systems in production
• Understanding of distributed systems and data infrastructure, and comfort with large-scale datasets and production systems

Required skills

• Strong Python and Spark
• Large-scale data processing frameworks such as Spark and Flink
• Workflow orchestration tools such as Airflow
• Machine learning workflows and model deployment