Lead Demand Forecasting Scientist - Perishable Goods

Farmer's Fridge; Chicago (IL); On-site; USD 160,000 - 170,000; Full time

Benefits offered by this job

Medical, dental, and vision insurance

401(k) with immediate employer match

Paid time off

Paid sabbatical after 5 years

Employee discounts

EAP

Job summary

Farmers Fridge is seeking a Lead Data Scientist, Demand to own the forecasting layer for fridge and retail demand. You will maintain and improve production models, forecast at scale across 2,000+ fridges and partner stores, and work closely with data engineers to run models in Snowflake and Dagster.

You will translate business rules into predictive models, measure impact on sales and waste, and contribute to company-level volume and revenue forecasting as models mature.

Qualifications

• 4-8 years building and maintaining forecasting or predictive models in production.
• Deep demand forecasting experience: time series, hierarchical, or ML-based methods.
• Comfort with count data and intermittent demand.

Responsibilities

• Own our fridge and retail demand forecasts end to end: data, features, model, validation, and production.
• Build forecasts that maximize contribution margin dollars and track impact on sell-through, unsolds and stockouts.
• Maintain and improve models in production and rebuild them when beneficial.
• Forecast at item, location, and day level across 2,000+ fridges and stores.
• Produce probabilistic forecasts to support optimization decisions.
• Collaborate with Data Engineering to run models in production pipelines (Snowflake, dbt, Dagster).
• Explain model expectations and trust to planners and operators.

Skills

Forecasting models

Python

SQL

Communication

Tools

Snowflake

dbt

Dagster

Job description

Farmers Fridge is seeking a Lead Data Scientist, Demand to own the forecasting layer for fridge and retail demand. You will maintain and improve production models, forecast at scale across 2,000+ fridges and partner stores, and work closely with data engineers to run models in Snowflake and Dagster.

You will translate business rules into predictive models, measure impact on sales and waste, and contribute to company-level volume and revenue forecasting as models mature.