[L6-2]Staff Data Scientist (SCM Systems)

Role Overview:

We seek an experienced Staff Data Scientist to drive innovation within our Supply Chain Management (SCM) technology team using advanced AI/ML and Operations Research. You'll primarily tackle challenges in inbound SCM (forecasting, inventory, purchasing) and Fulfillment Center operations, with opportunities across Marketing, Retail, and Last-Mile. Collaborating cross-functionally, you will rapidly design, build, and deploy production-ready solutions, playing a key role in shaping and executing our SCM automation strategy and directly impacting business outcomes

What You Will Do:

• Explore & Define Opportunities: Conduct Exploratory Data Analysis (EDA) using statistical techniques (e.g., histograms, boxplots, correlation analysis) and collaborate cross-functionally to translate business needs into well-defined data science problems with clear success metrics (e.g., precision, recall, RMSE, cost reduction).
• Design & Build Models: Develop and implement sophisticated models tailored to SCM challenges. This includes applying Machine Learning techniques (e.g., tree-based models like XGBoost/LightGBM, regression methods, deep learning like RNNs/LSTMs for forecasting) and/or Operations Research approaches (e.g., Mixed-Integer Programming (MIP), Linear Programming (LP), simulation) using tools like Python libraries (Scikit-learn, TensorFlow, PyTorch) and solvers (e.g., Gurobi, CPLEX).
• Prototype, Test & Validate: Build model prototypes, conduct rigorous offline validation and backtesting, and design/analyze online experiments (A/B tests) to prove the efficacy and business value of your proposed solutions before full-scale deployment.
• Deploy & Integrate: Work closely with ML Engineers and Software Engineers to deploy validated models into scalable, production-grade systems, ensuring proper integration with upstream data sources and downstream operational applications. Contribute to MLOps practices for robust deployment and maintenance.
• Monitor & Iterate: Establish automated monitoring dashboards and alerts for model performance and data drift. Analyze results, troubleshoot issues, and iteratively improve models based on ongoing performance and evolving business requirements.
• Communicate & Influence: Clearly document methodologies, present findings, and explain complex models to diverse audiences (technical and non-technical) to drive adoption and inform strategic decisions. Provide technical guidance and mentorship within the team.

Essential Qualifications

• Master’s degree or PhD in a quantitative field (e.g., Computer Science, Operations Research, Statistics, Engineering, Economics, Physics, Mathematics).
• + years of hands-on industry experience applying data science, ML, and/or OR techniques, including deploying models into production.
• Proven ability to independently scope, design, build, deploy, and monitor data science models/solutions.
• Strong programming proficiency in Python for data analysis (Pandas, NumPy), ML (Scikit-learn, TensorFlow/PyTorch/Keras), and experience with relevant OR solvers/libraries (e.g., Gurobi, CPLEX, PuLP, SciPy.optimize).
• Experience querying and manipulating large datasets using SQL and distributed computing frameworks (e.g., Spark, Dask).
• Understanding of core ML algorithms (trees, regressions, clustering, NNs), statistical modeling, optimization techniques (LP, MIP), and experimental design (A/B testing, causal inference basics).
• Excellent problem-solving, critical thinking, and communication skills.

Preferred Qualifications:

• PhD in a relevant quantitative field.
• Deeper theoretical understanding and practical expertise in core ML algorithms, statistical modeling, optimization techniques, and experimental design/causal inference.
• Experience specifically within Supply Chain Management (inbound forecasting, inventory optimization, purchasing automation, network design, FC operations), Logistics, or E-commerce.
• Demonstrated experience leading complex data science projects end-to-end.
• Deep expertise in specific areas like time-series forecasting (e.g., ARIMA, Prophet, DeepAR), inventory theory, large-scale optimization, reinforcement learning, or simulation.
• Experience with cloud platforms (AWS, GCP, Azure) and MLOps tools/practices (e.g., MLflow, Kubeflow, model versioning, CI/CD).
• Proficiency in other programming languages relevant to data science or backend development (e.g., Java, Scala, Go).
• Experience mentoring junior data scientists or engineers.