Design and lead the development of high-performance ML systems for predictive analytics, optimization, and anomaly detection at scale. The role involves architecting production-grade ML pipelines and managing multiple data modalities.
Core Responsibilities
Architect end-to-end ML pipelines for high-frequency operational datasets.
Design automated retraining, drift detection, and feature store management.
Apply causal inference and probabilistic modeling for root cause analysis.
Mentor ML engineers and enforce best practices in reproducibility and testing.
Collaborate with business stakeholders to translate ML outcomes into actionable KPIs.
Required Technical Skills
Languages & Frameworks: Python, SQL, scikit-learn, XGBoost, LightGBM.
Time-Series: ARIMA, Prophet, LSTM.
Causal & Probabilistic Modeling: PyWhy, Bayesian Networks.
Data Handling: Pandas, NumPy, PySpark.
Evaluation: Cross-validation, ROC, MAE, RMSE, SHAP/LIME explainability.
Advanced Skills: Ensemble modeling, AutoML, interpretability (SHAP, ELI5).
MLOps & Scaling: Kubeflow, Airflow, MLflow, Docker, FastAPI, CI/CD pipelines.
Cloud & Compute: Azure ML, AWS SageMaker, or GCP Vertex AI.
Python, SQL, Scikit-Learn, XGBoost, LightGBM, ARIMA, Prophet, LSTM, PyWhy, Bayesian Networks, Pandas, NumPy, PySpark, Cross-Validation, ROC, MAE, RMSE, SHAP, LIME, Ensemble Modeling, AutoML, ELI5, Kubeflow, Airflow, MLflow, Docker, FastAPI, CI/CD Pipelines, Azure ML, AWS SageMaker, GCP Vertex AI