• Co-design and implement QA workflows using statistical diagnostics, validation rules, and anomaly detection techniques
  • Apply AI/machine learning tools to identify inconsistencies, missing values, or suspicious patterns in large-scale asset datasets
  • Build reusable QA tools in Python or R that can be automated and scaled across internal pipelines
  • Work with other research teams, our development team, and other stakeholders so that they can make best use out of the asset location data
  • Contribute to model documentation, reproducibility, and version control of data science assets.