Machine Learning Engineer
- East Bay, CA, United States
- San Francisco, CA, United States
- Silicon Valley, CA, United States
- Austin, TX, United States
- Apache Spark
Afresh is on a mission to reduce food waste and increase access to nutritious food globally by transforming the fresh food supply chain. Our solution is currently deployed in hundreds of grocery stores across the United States and is on track to reduce 30 million pounds of food waste per year with our existing customers alone. By 2021, we're aiming to reduce food waste by a quarter billion pounds per year.
The Modeling and Optimization 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.
You will be working on pushing the boundaries of our system's performance on product categories we're already live in, as well as expanding our product to entirely new categories. You will be responsible for implementing new systems end-to-end, including working with product teams to define the business needs of a solution, reviewing research papers and implementing novel ideas, and scaling up experiments to generate predictions and decisions on millions of items every day. 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.
What you will do:
-In your first 3 months, you will experiment with new features, train and validate new models, and push updates to all of our customers. You will build a strong understanding of perishable inventory control, time series forecasting, and simulation techniques.
-By the end of your first 6 months, you will have proposed, implemented, and rigorously tested algorithmic or engineering improvements to our core models, featurization, or automatic training and experimentation systems.
-By the end of your first year, you will have implemented new modeling techniques, expanded our product offering to new categories with novel algorithms, and scaled your solution to our entire customer base.
-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 day, and so your code must be rigorously validated, tested, and bug-proof. This is not an analytics team.
What skills and experience do you need?
-2+ years of professional software development experience with advanced machine learning or statistical and numerical optimization methods.
-You have repeatedly and successfully taken complex research ideas from experiment to production, and you write high-quality and high-performance code that lives outside of experiments.
-Familiarity with forecasting techniques, time series analysis, and large-scale stochastic optimization is a plus.
-A graduate degree in operations research, computer science, electrical engineering, statistics, or similar quantitative field is a plus.
About Afresh Technologies
Afresh is a revolutionary new approach to fresh ordering, forecasting, and store operations for grocery retailers. Using cutting-edge technology (AI, ML, deep reinforcement learning, etc.), we build tools that help grocers and other supply chain constituents reduce food waste and maximize profit by forecasting demand and optimizing decisions.
Our four cultural values are: Humility, Proactivity, Humility and Kindness.
- Apache Spark
Skip straight to final-round interviews by applying through Triplebyte.