Staff Applied Scientist

• Lead R&D for core replenishment AI/ML models, defining the modeling roadmap across demand forecasting, inventory optimization, and decision-making policy.
• Model complex problems such as inventory decay, promotions, price elasticity, and inventory uncertainty, implementing solutions to multi-stage and multi-echelon inventory optimization problems.
• Drive fundamental changes to the core system from research through production, writing rigorously tested and scalable code.
• Mentor scientists and engineers, set standards for experimental rigor, and push the boundaries of AI capabilities.

This role directly reduces food waste by optimizing fresh food ordering, preventing over 200 million pounds of waste annually, and ensures fresher, healthier produce for millions of people.

• MS or PhD in Operations Research, Industrial Engineering, Computer Science, Electrical Engineering, or another quantitative field, or equivalent practical experience.
• For MS candidates: 8+ years industry experience; for PhD candidates: 4+ years industry experience.
• Experience researching and building systems for large-scale decision making under uncertainty.
• Prior experience in inventory optimization, supply chain management, forecasting, stochastic optimization, or related fields is a plus.
• Ability to independently deliver high-quality software implementations in the Python data stack (numpy/torch/pandas/etc).

Comprehensive health & wellness coverage, competitive base salary with meaningful equity (U.S. employees), 401(k) with company match, flexible remote work with home office stipend and coworking wallets, annual professional development budget, monthly stipends for wellness and telecommunications, and flexible PTO.

Salary range in Canada: $169,000 - $252,000 CAD (dependent on experience).

Afresh Technologies uses AI to reduce food waste in the grocery industry, providing a platform that optimizes fresh food ordering and supply chain decisions, preventing over 200 million pounds of food waste annually.