Description

You will build and maintain ML solutions for hyper-personalization in financial services, integrating models with multiple data sources.

This role is on-site.

Responsibilities

• Fine-tune existing models to optimize performance and adapt to evolving requirements.
• Design and implement ETL processes and data pipelines to support model integration.
• Manage ML models in production using MLOps practices for monitoring and tracking.
• Drive architecture and engineering best practices for the integration framework.

Required Skills

• Proficiency in Python and SQL databases.
• Experience with AWS services: SageMaker, Lambda, Glue, S3, IAM, CodeCommit, CodePipeline, and Bedrock.
• Experience with data pipeline and workflow management using Apache Airflow or AWS Step Functions.
• Knowledge of ETL techniques, data modeling, and data warehousing.
• Familiarity with AI/ML platforms such as TensorFlow, PyTorch, and MLflow.
• Understanding of MLOps practices, including model monitoring and data drift detection.
• Experience with Docker and AWS ECR for containerization.

Preferred Skills

• Experience in financial services domain.
• Knowledge of hyper-personalization algorithms.

Key Skills

Education

Any graduate