Perennial Systems is looking for a skilled Machine Learning Engineer with hands-on experience deploying models on Google Cloud Platform (GCP) using Vertex AI. This role involves enabling real-time and batch model inferencing based on specific business requirements, with a robust focus on production-grade ML deployments.
Key Responsibilities:
- Deploy machine learning models on GCP using Vertex AI.
- Design and implement real-time and batch inference pipelines.
- Monitor model performance, detect drift, and manage lifecycle.
- Ensure adherence to model governance best practices and support ML-Ops workflows.
- Collaborate with cross-functional teams to support Credit Risk, Marketing, and Customer Service use cases, especially within the retail banking domain.
- Develop scalable and maintainable code in Python and SQL.
- Work with diverse datasets,
perform feature engineering, and build, train, and fine-tune advanced predictive models.
- Contribute to model deployment in the lending space.
Skills to have:
- Strong expertise in Python and SQL.
- Proficient with ML libraries and frameworks such as scikit-learn, pandas, NumPy, spaCy, CatBoost, etc.
- In-depth knowledge of GCP Vertex AI and ML pipeline orchestration.
- Experience with ML-Ops and model governance.
- Exposure to use cases in retail banking—Credit Risk, Marketing, and Customer Service.
- Experience working with structured and unstructured data.
Nice to Have:
- Prior experience deploying models in the lending domain.
- Understanding of regulatory considerations in financial services.