Data Scientist - Python

VAM Systems

Design, build, and optimize predictive models and machine learning algorithms using structured and semi-structured data.

Perform data pre-processing, feature engineering, and model selection independently.

Build and maintain automated model pipelines including training, validation, scoring and monitoring.

Implement model drift detection, retraining logic, and performance diagnostics.

Conduct code-based model explainability (eg. SHAP, LIME), support documentation for governance review.

Expertise Required

Advanced proficiency in Python (Pandas, NumPy, Scikit-leam, XGBoost, LightGBM)

Strong command of SQL arid handling large datasets (via warehouse or lake)

Experience deploying models using MLflow, Airflow, Docker, or similar tools

Familiarity with model performance metrics (ROC AUC, F1, lift/gain, etc.)

Hands-on in training and evaluating models for binary classification, multi-class, regression, or time series

Exposure to deep learning (PyTorch or Tensorflow) for advanced use cases