Job Description
- Data preparation: pull, clean, and join datasets from ERP, CRM, and production databases using Python and SQL
- Exploratory analysis & ML prototyping: run EDA, build features, and prototype supervised or unsupervised models as specified in the hypothesis
- Validation and visualization: validate model outputs against process logic and plant values, create charts, short reports, and dashboards for chemists & engineers to review
- Contribute to pipelines: write modular, documented code, ensure version control in Git, and update experiment tracking
- Support operations: maintain monitoring dashboards in AWS, prepare test data for deployment, propose small code or data quality improvements