Data Scientist — Demand Forecasting

Hangul AI

Hybrid (Chicago, US) · $98K – $118K · Full-time · Posted 6 months ago

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

About the role

This is an operations-heavy data science role inside a building materials distributor with 61 branches across the Midwest. The team needs better demand forecasts for purchasing and replenishment, especially across products with strong seasonal and regional patterns. You would work with branch and supply teams, using transactional and inventory data to improve forecast quality and reduce stockouts and excess inventory. The environment is practical, not research-led. Stakeholders expect models they can question and understand.

Responsibilities

Build branch- and SKU-level demand forecasts used by procurement and replenishment teams
Analyse forecast error drivers including seasonality, weather, promotions, and one-off project demand
Partner with operations leaders to define practical decision rules around model outputs
Develop monitoring for forecast drift and model performance by branch and category
Document model assumptions and handoff logic clearly enough for planning teams to use with confidence

Requirements

3–5 years of data science in forecasting, supply chain, retail, or operations analytics
Python for modelling, feature engineering, and reproducible analysis
SQL for extracting sales, inventory, and branch-level operational data
Pandas and Scikit-learn for baseline modelling and experiment iteration
Statistics you can explain to non-technical operators, including uncertainty intervals and forecast error trade-offs
Experience working with messy transactional data and changing business assumptions