Afresh: Machine Learning Engineer

Seeking a Machine Learning Engineer to join founding-team for developing predictive models for the food supply chain, including forecasting demand, prices, inventory, etc. using deep learning combined with Bayesian statistics, causal inference, and other techniques.

At: AfreshAfresh
Location: San Francisco, CA
Position: Machine Learning Engineer

Email Matt Schwartz, CEO,

Help us build our core AI technology.


About 30-40% of food produced worldwide is thrown away, causing nearly a trillion dollars of economic losses, trillions of gallons of wasted water, and billions of tons of greenhouse gas emissions. In the US, about 40% of all food waste occurs at the retail level and downstream, largely driven by insufficient technology and manual processes. That’s what we’ve set out to solve: Afresh uses deep reinforcement learning to power tools that help grocers and other supply chain constituents reduce food waste by forecasting demand and optimizing decisions. In a partnership with a large regional grocery chain, the Afresh system demonstrated the potential to reduce waste by up to 80% while substantially increasing the retailer’s profits (to the tune of $10s of millions). We are now deployed live at that chain and are adding additional grocery chains as partners.

What’s the opportunity?

As an early technical hire you will have significant influence on the future shape and style of our organization--we just closed our Seed round of financing in January from Steve Anderson of Baseline Ventures (Instagram, SoFi, Heroku, Stitch Fix), Innovation Endeavors, and strategic angels.

You’ll join a passionate founding team with strong domain expertise (Stanford MBAs, careers spent in food and tech) and strong technical skills (Stanford PhD CS/AI and Stanford BS/MS in Engineering).

What will you be doing?

  • Developing predictive models for the food supply chain. Forecasting demand, prices, inventory, etc. using deep learning combined with Bayesian statistics, causal inference, and other techniques.
  • Training reinforcement learning agents to plan supply chain decisions pertaining to food production, ordering, pricing, delivery, etc.
  • Scaling machine learning systems to hundreds of gigabytes of data and assisting with the development of cloud infrastructure that makes this possible.
  • Building visualization and data exploration tools. Evaluating and iterating on new models.

What skills do you need?

  • Bachelor’s, master’s, or PhD in computer science, statistics, math, or equivalent.
  • Excellent programming and software design skills, particularly in Python.
  • Strong understanding of machine learning, particularly deep learning, reinforcement learning, probabilistic models, Bayesian statistics.
  • Expertise with the Python machine learning and deep learning stack: numpy, scipy, pandas, sklearn, matplotlib, tensorflow, keras, pytorch.
  • Experience with time series, latent-variable probabilistic models, or reinforcement learning in partially observed domains are pluses.

Interested? Email us at: