AI Fresh Produce Waste Reduction Optimizer

Halvex Data

Remote · $80k – $100k / year · Full-time · Posted 4 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

Forty percent of all fresh produce in the US is wasted between farm and consumer. A significant portion of that waste happens at the retail stage: stores over-order because demand forecasts don't account for local weather, competitive promotions, or hyperlocal events, and they under-order because they don't have confidence in their forecasts. Better forecasting directly reduces waste and improves margin. We serve 65 grocery chains and fresh food retailers. Our demand forecasting stack handles packaged goods well. Fresh produce is harder: shelf life varies by product category and storage condition, display placement affects sell-through rate, and the cost of a stockout differs dramatically between a banana and a specialty mushroom. A model that treats all SKUs uniformly leaves significant optimization on the table. You'll build the fresh produce specific optimization layer: shelf life-adjusted demand forecasting that accounts for remaining sellable days, dynamic replenishment recommendations that balance waste risk against stockout probability, and markdown timing recommendations that maximize sell-through before spoilage. The metric that matters is produce gross margin after waste — you'll own it.

Fully remote.

Responsibilities

Build shelf life-adjusted demand forecasting incorporating remaining sellable days and spoilage risk
Implement dynamic replenishment recommendations balancing waste risk against stockout probability
Design markdown timing models maximizing sell-through value before spoilage threshold
Develop SKU-level waste tracking connecting forecast accuracy to realized waste outcomes
Create display placement recommendations based on sell-through rate correlations
Monitor fresh produce gross margin improvement as the primary optimization metric

Requirements

3+ years in supply chain analytics, retail data science, or demand forecasting
Strong Python and SQL skills with time-series and inventory optimization experience
Understanding of fresh produce retail operations and spoilage dynamics
Experience building optimization models that account for multiple competing objectives
Ability to connect ML model improvements to measurable P&L outcomes