Lead Data Scientist, Demand

Farmer's Fridge Careers•Chicago, IL

14d•$160,000 - $170,000•Onsite

About The Position

Farmer’s Fridge is hiring its first full-time data scientist dedicated to demand planning. The Lead Data Scientist, Demand owns the predictive models that forecast what will sell, where, and when across the company’s network of more than 2,000 Smart Fridges and retail partner stores. The role maintains and improves existing fridge and retail forecasting models in production, rebuilds them where a better approach would pay off, and later expands into company-level volume and revenue forecasting. The position works closely with the Lead Decision Scientist, who owns the prescriptive layer that turns forecasts into stocking, allocation, and routing decisions. It also partners with Data Engineering to operate models in production and with the Manager, Demand Planning and other planning, supply chain, operations, and Channel Strategy colleagues who use or set business objectives for forecasts. The role translates business rules and operating constraints into models, evaluates whether those rules are supported by data, and sets technical standards for forecasting. The work focuses on item-, location-, and day-level forecasts, including low-volume and intermittent demand. Models must account for issues such as stockouts that conceal demand, short shelf life, new locations and menu items, holidays, and promotions. The role emphasizes probabilistic forecasts and business outcomes—including sell-through, waste, lost sales, and contribution margin—rather than statistical accuracy alone. It also establishes backtesting, monitoring, model scorecards, documentation, and a repeatable process for measuring and shipping model changes. This is an in-office role based in Chicago, or for someone willing to relocate. The base salary range is $160,000–$170,000, with eligibility for company performance-based bonuses and equity.

Requirements

4–8 years of experience building and maintaining forecasting or predictive models in production.
Deep demand forecasting experience using time-series, hierarchical, or machine-learning methods such as gradient boosting, state-space, or Bayesian methods.
Comfort working with count data and intermittent demand, such as Poisson or negative binomial approaches.
Experience correcting for censored demand caused by stockouts, or a strong grasp of why it matters.
Strong Python and SQL skills.
Experience with Snowflake or a similar cloud data warehouse.
Rigor in backtesting and experiment design, with the ability to demonstrate that a model change helped.
Track record of owning model work end to end, from problem framing through production and monitoring.
Ability to identify a shipped model change and explain the business result it moved in dollars.
Clear communication skills, including explaining forecast uncertainty and tradeoffs to planners and operators and defending modeling choices to technical peers.
Comfort working in a fast-paced environment and setting direction.
Familiarity with using AI tools in day-to-day work.
Based in Chicago or willing to relocate; the role is in-office.

Nice To Haves

Forecasting experience with perishable goods, grocery, CPG, food service, or multi-location retail.
Exposure to how forecasts feed optimization models for inventory, allocation, or routing.
Causal inference experience, such as difference-in-differences or matched controls, for measuring pricing, promotion, or operational changes.

Responsibilities

Own fridge and retail demand forecasts end to end, including data, features, models, validation, and production.
Build forecasts that maximize contribution margin dollars and track impact through sell-through, unsolds, and stockouts against Channel targets.
Forecast at the item, location, and day level across more than 2,000 fridges and retail partner stores, including low-volume and intermittent demand.
Model stockouts and censored demand, short shelf life, new fridge ramp-ups, new menu items, holidays, and promotions.
Produce probabilistic forecasts so optimization models can weigh lost-sale costs against waste costs.
Maintain and improve production models, and rebuild them where a better approach clearly pays off.
Partner with the Lead Decision Scientist on forecast outputs needed by the optimization solver, and measure how forecast changes affect stocking decisions and results.
Build backtesting and monitoring, evaluating business outcomes such as sell-through, waste, and lost sales as well as statistical error.
Run a recurring model scorecard with Channel Strategy and Demand Planning; measure material model changes before and after in sell-through, unsolds, stockouts, and contribution margin per fridge per week.
Partner with Data Engineering to run models in production pipelines using Snowflake, dbt, and Dagster, without manual babysitting.
Work with demand planning, supply chain, and operations to explain model expectations, rationale, and uncertainty.
Measure the value of planner overrides, incorporate consistently beneficial overrides as explicit rules, and retire overrides that do not help.
Expand into company-level volume and revenue forecasting as the core models mature.
Maintain documentation of each business rule in the models, including its purpose, origin, owner, and last change.
Set standards for how forecasting models are built, tested, documented, and shipped at Farmer’s Fridge.

Benefits

Company performance-based bonuses and equity eligibility.
Medical, dental, and vision insurance, with multiple plans available.
401(k) with immediate employer match vesting.
Paid time off, including vacation, sick leave, and holidays.
Paid sabbatical after five years of service.
Employee discounts.
Employee Assistance Program (EAP).
Daily Farmer’s Fridge meals and office snacks.
Regular business updates and cross-functional collaboration, with open access to leadership.
Employee input in menu creation, including regular tasting panels.