Software Engineering

Senior Machine Learning Engineer

South San Francisco, CA


At Plenty, we’re on a mission to give people in local communities everywhere access to the freshest, most amazing tasting produce possible. And to do so in a way that’s better for the planet.

The people and teams who make up Plenty are at the core of how we do that. We are an ag-tech company looking for a Machine Learning Engineer to join the Software and Data team who will advance Plenty's mission through the development and application of advanced custom algorithms that support critical farm systems. The Machine Learning Engineer will work in a heavily cross-functional environment to rigorously develop and deploy models that will drive physical outcomes by controlling the systems and automation equipment in our farms. Plenty's opportunities to apply Machine Learning are diverse – our data include images, hyperspectral image cubes, time-series, continuous and discrete numerical, categorical, and text. The Machine Learning Engineer also supports a culture where machine learning isn't considered magic or a an esoteric research topic but rather a rigorous engineering practice that impacts our real physical farms. Did we mention we're deploying ML models that drive physical systems?

About Role

This is a technical role responsible for building sophisticated data products and analyses which are not possible without a strong, specialized team. The ideal candidate takes pride in her/his work and possesses strong analytical ability, the capacity to translate fuzzy requirements into actionable, technical solutions, the capacity to explain solutions to people with other domain expertise, and an attention to detail. She/he appreciates an environment where superior work is encouraged, noticed, and rewarded and where individuals carry significant responsibility. The ideal candidate is uncommonly self-motivated and feels tremendous ownership over outcomes regardless of where in the organization solutions may lie.

What You'll Do

  • Identify and develop machine learning based solutions to a wide variety of problems

  • Develop data-driven models for descriptive, diagnostic, predictive and prescriptive analytics

  • Develop image classification models

  • Develop time-series anomaly detection models

  • Establish reusable data processing pipelines to enable rapid re-training and iteration through different ML methodologies

  • Design experiments and analysis methodologies that are statistically rigorous


What We're Looking For

  • 5+ years of relevant work experience
  • Exemplary verbal and written communication skills

  • Strong proficiency with data analysis languages such as R and Python

  • Excels in documentation of methods, analysis and results

  • Experience working with 'messy' datasets

  • Experience with TensorFlow, Keras, Caffe, Torch, Scikit-Learn, or Theano frameworks

  • Experience with deep learning, feature learning, anomaly detection, boosting, and decision trees

  • Experience with R/Python package/module development

  • Experience with R Markdown or Jupyter notebooks

  • Experience with Shiny or Dash app development a plus

  • Experience with factory organizations and operations a plus

  • Experience selecting and using AWS or similar cloud-based compute to train models

  • Proficiency in statistical analysis and data visualization

  • Ability to work under pressure while managing competing demands and tight deadlines

  • Strong organizational skills with meticulous attention to detail


About Plenty

Plenty is here to change the way people eat, making extraordinary flavor and nutrition more available in a way that's better for people and the planet. We build farms that can put craveable flavor first while delivering exceptional yields. And our produce is always pesticide-free and grown using less than 1% of the land and 5% of the water of outdoor farming.

Share this job