End-to-End Product Ownership: Lead the development of predictive models from exploration and prototype to full-scale production deployment.
Prediction: Build robust regression and/or time-series and/or deep learning models to predict prices/values of financial assets, oil, apparel, and other commodities.
Model Optimization: Continuously monitor and fine-tune models for accuracy, performance, and scalability using real-time data feedback.
ML Ops & Deployment: Collaborate with engineering to ensure successful deployment and monitoring of models in production environments.
Stakeholder Collaboration: Translate business problems into analytical frameworks, working closely with product, strategy, and business teams.
Data Strategy: Define and manage pipelines and feature stores using structured and unstructured data sources.
Required Qualifications
8+ years of experience in data science, with a strong background in predictive analytics and machine learning.
Proven experience building and scaling ML models in production environments (not just notebooks or PoCs).
Deep expertise in Python, SQL, and ML libraries (e.g., scikit-learn, XGBoost, LightGBM, TensorFlow/PyTorch).
Strong knowledge of regression techniques, time-series forecasting, and feature engineering.
Experience in domains such as finance, commodities, retail pricing, or demand prediction is highly preferred.
Experience working with cloud platforms (Azure, AWS or GCP), Azure ML or Sagemaker, tools like Airflow, Docker, and MLflow.
Ability to define success metrics, conduct A/B tests, and iterate based on measurable KPIs.
Excellent communication and storytelling skills with both technical and non-technical stakeholders.