Trend Micro is a global cybersecurity leader focused on building cutting-edge AI applications and services. The ML Data Engineer will contribute across the full machine learning lifecycle, driving innovation in AI for cybersecurity and advancing techniques to secure AI applications.
Responsibilities:
- Design and build feature engineering pipelines, create domain-specific features, implement feature stores, and ensure consistency across training and inference
- Build scalable preprocessing pipelines handling missing values, outliers, normalization, and validation. Implement quality metrics to detect data quality issues, biases, and drift. Ensure proper handling of imbalanced datasets and high-cardinality variables while preventing data leakage
- Conduct exploratory analysis to understand data patterns and trends. Profile and optimize data workflows for performance, speed, and resource efficiency. Analyze model performance feedback to iteratively refine features and preprocessing strategies
- Collaborate with data, ML engineers, and scientists to translate business needs into features. Ensure preprocessing consistency, document feature definitions and transformations, and develop reusable libraries to promote best practices