About the Role
The Prediction, Optimization, and Planning (POP) team builds Afresh's core replenishment technology. Our models are directly responsible for ordering millions of dollars of fresh inventory across the world every day. Fresh food ordering is an extremely complex high-dimensional decision-making problem. We face the complex challenges presented by decaying product, uncertain shelf lives, varying consumer demand, stochastic arrival times, extreme weather events, and tight performance constraints (to name a few). We tackle these problems with a mix of machine learning, large-scale simulation, and optimization technologies.
As an Applied Scientist at Afresh, you will take your existing knowledge of forecasting, simulation, and stochastic optimization and apply it to the challenging and important problem of perishable inventory control. You will research, implement, and rigorously validate improvements to our core replenishment system. This will include modeling consumer demand, item-level perishability, and complex multi-echelon supply chains. Your work will be visible from day one, will make a substantial impact on decreasing food waste, and will lead to fresher, healthier produce for millions of people across the world.
- You will work on improving the core models of our system: demand forecasting, inventory optimization, and simulation. You will also lead research development for new product and business challenges. You will model the complex problems of inventory decay, promotions, price elasticity, and inventory uncertainty, and implement solutions to multi-stage and multi-echelon inventory optimization problems.
- In your first 3 months, you will acquire an encyclopedic knowledge of perishable inventory control and Afresh's core decision making problem. You will gain proficiency in our data manipulation, transformation, and simulation tools, and you'll test an experimental improvement to our demand forecasting, ordering, or simulation models.
- By the end of your first 6 months, you will have proposed, implemented, and rigorously validated an improvement to our core modeling system.
- By the end of your first year, you will have led the implementation of fundamental changes to our core system and led research into new product areas (warehouse level replenishment, production planning).
- We need to make optimal ordering decisions for millions of items for weeks at a time, and our system must be fault-tolerant to an extreme. Our partners rely on our system to order millions of dollars of inventory every week, and so your code must be rigorously validated, tested, and bug-proof.
Skills and Experience
The following represents attributes our ideal candidate possesses. We encourage all highly qualified candidates to apply, even if they do not fulfill all the listed criteria
- 5+ years of industrial or academic experience building systems that deal with large-scale decision making under uncertainty. Some possible prior research areas are inventory optimization, supply chain management, network optimization, forecasting, game theory, decision analysis, or stochastic and approximate dynamic programming.
- Excellent communication and presentation skills. You should be able to explain complex mathematical ideas to product teams in plain English and easily translate business requirements into constrained optimization problems.
- Ability to independently deliver high quality software implementations of your solutions in the Python data stack (numpy/torch/pandas/etc).
Afresh is on a mission to reduce food waste and increase access to nutritious food globally by transforming the fresh food supply chain. Our AI-powered solutions optimize the multi-trillion-dollar grocery industry's food ordering, production, and merchandising processes. We built the first platform capable of handling all of Fresh food’s complexities.