Machine Learning Engineer II, Quản lý chi tiêu

• Take ownership of the end-to-end machine learning lifecycle for tabular data, from research, dataset preparation, feature engineering, and model training to high-performance deployment and production monitoring across domains such as  transaction categorization, recurring transaction prediction.

• Bridge the gap between AI research and production engineering by designing rigorous experimental frameworks, optimizing model inference latency, and ensuring continuous model reliability.

Mô tả công việc

• Implement Machine Learning algorithms (XGBoost, LightGBM, CatBoost, Neural Networks) to enhance model performance for existing products .

• Be thoroughly familiar with modeling lifecycle from data gathering, feature engineering, and cleansing to model training, validation, monitoring and error analysis to ensure model robustness and generalization.

• Design scalable feature extraction pipelines, handle complex data quality issues, missing values, high-cardinality categorical variables, and severe class imbalance (SMOTE, Focal Loss, class weighting).

• Collaborate with engineering and product teams to integrate model API endpoints into core products.

• Review and reproduce recent research (tabular machine learning / deep learning, time-series forecasting, and interpretability (SHAP / LIME)), propose modeling improvements, and communicate findings through technical reports and presentations.

Yêu cầu công việc

• Bachelor’s degree in Computer Science, Engineering, Mathematics, Data Science, or a related field.

• 3+ years of industry experience in software engineering/machine learning;

• Strong Python skills and hands-on experience with tabular processing libraries (Pandas, NumPy, Scikit-Learn, PySpark/Polars) and GBDT frameworks (XGBoost, LightGBM, CatBoost).

• In-depth understanding of the complete modeling lifecycle: data gathering, feature engineering, hyperparameter tuning, model serving, and post-deployment monitoring.

• Proficiency in PyTorch or TensorFlow for building custom neural architectures and tabular deep learning models.

• Ability to read, reproduce, and extend recent research papers.

• Strong analytical, problem-solving, and cross-functional collaboration skills.