What are the responsibilities and job description for the Senior Data Scientist position at Prodapt?
We are seeking a highly skilled Data Scientist with expertise in demand forecasting, supply chain optimization, and retail inventory management. In this role, you will develop, retrain, and validate demand forecasting models tailored to multiple regional markets, while collaborating closely with the optimization team to enhance inventory allocation and replenishment strategies. You will work with large-scale retail datasets, deploy models using AWS SageMaker, and operate within a federated data architecture to ensure accurate, scalable forecasting solutions.
Key Responsibilities:
- Develop, retrain, and adapt demand forecasting models (ARIMA, Prophet, neural networks) to reflect regional seasonality, buying patterns, and lead times.
- Calibrate and validate forecast accuracy using federated regional data to meet go-live thresholds before market activations.
- Collaborate with the supply chain optimization team to provide inputs for inventory allocation and replenishment engines.
- Translate complex business constraints into mathematical optimization models using linear programming and constraint satisfaction techniques.
- Design and implement optimization solutions for retail inventory allocation and replenishment using Python libraries (PuLP, OR-Tools) and solvers (Gurobi, CPLEX).
- Deploy and maintain forecasting and optimization models on AWS SageMaker, integrating with Lambda and other AWS services for scalable workflows.
- Work independently with architectural guidance from lead scientists, and mentor junior applied scientists as needed.
- Communicate model insights and business impact effectively to cross-functional teams.
Required Qualifications:
- Strong experience in time series forecasting methods such as ARIMA, Prophet, and neural forecasting models (LSTM, RNN).
- Proficiency in mathematical optimization techniques including linear programming, constraint satisfaction, and multi-objective optimization.
- Hands-on experience with Python and relevant libraries: pandas, numpy, scikit-learn, statsmodels, PuLP, OR-Tools.
- Familiarity with optimization solvers such as Gurobi or CPLEX.
- Experience working with large-scale retail datasets and federated data architectures.
- Expertise in retail demand planning, demand sensing, and supply chain or inventory management.
- Proficient in AWS ML stack, especially SageMaker for model training and deployment, and Lambda for serverless integration.
- Strong SQL skills for data extraction and manipulation.
- Ability to translate business requirements into mathematical and computational models.
- Excellent problem-solving skills and ability to work independently.
- Experience mentoring or leading applied scientists is a plus.
- Advanced degree (MS or PhD) in Operations Research, Applied Mathematics, Computer Science, or related field.
Preferred Qualifications:
- Experience with store allocation and replenishment systems.
- Familiarity with agentic AI frameworks or advanced AI-driven decision-making systems.
- Knowledge of CI/CD pipelines for ML model deployment.
- Multi-market or international retail exposure.