Data Scientist – Inventory Planning and Control

Overview

Role Overview

We are looking for a Data Scientist to help optimize and scale existing inventory planning systems across an omni-channel retail environment spanning online and offline stores.

You will work on improving allocation, replenishment, assortment, and demand forecasting algorithms, partnering closely with business and engineering teams to drive measurable improvements in availability, inventory efficiency, and sell-through.

What You’ll Do

• Build and optimize algorithms for inventory allocation, replenishment, and assortment planning across online and offline stores
• Improve demand forecasting models, accounting for seasonality, new launches, promotions, and regional demand patterns
• Partner with Merchandising, Supply Chain, and Retail Operations to translate business problems into data-driven solutions
• Design and maintain scalable data pipelines and dashboards tracking key metrics such as sell-through, stock-outs, and inventory turns
• Use experimentation, back-testing, and simulations to continuously refine replenishment and distribution logic
• Contribute to an end-to-end ML ecosystem, including feature engineering, model deployment, monitoring, and performance evaluation

What You’ll Bring

• 5–7 years of experience in data science, supply chain analytics, or demand forecasting
• Strong foundation in Python and machine learning frameworks (e.g., scikit-learn, XGBoost)
• Hands-on experience with time-series forecasting, optimization techniques, and simulation modeling
• Comfort working with large, messy, real-world datasets (sales, inventory, locations, product hierarchies)
• Strong analytical thinking with the ability to communicate insights clearly to non-technical stakeholders

Bonus Points For

• Experience with inventory replenishment or allocation systems in omni-channel environment (in-house or vendor-built)
• Exposure to MLOps practices or production ML systems
• Familiarity with cloud platforms (GCP, AWS) and data tools such as Airflow, BigQuery, Databricks

What Success Looks Like

• Measurable improvements in forecast accuracy and bias
• More efficient inventory allocation and replenishment decisions
• Scalable models that reliably support omni-channel operations