Digital Harvest, Inc.

Data Scientist

Digital Harvest, Inc.

International, Anywhere; 100% Remote

March 11, 2022

Digital Harvest is expanding our team with additional software engineers and data scientists!

We are a young company that applies remote sensing and data science techniques to solve large-scale problems in the agricultural sector. Our customers are large growers and processors of food and/or industrial crops produced on hundreds of thousands of hectares of farmland seeking to better understand resources, costs, and yield qualities and quantities.

Data of agronomic significance is fused to perform data analysis and visualization, feature extraction, and supervised machine learning to create predictive models for rapid use in the customers’ decision process. These projects start with a pilot project to demonstrate viability and transition to digital agriculture consulting and solutions development.

Digital Harvest is a growing company seeking individuals to grow with us, and willing to provide an environment of on-the-job learning to continue driving that growth. This is a flexible position that can be filled at entry-level or mid-level.

Since we are a small team there are plenty of opportunities to grow, make highly valuable contributions and take ownership of projects. Our team works highly autonomously with little need for formal meetings and direct supervision. If high freedom, high responsibility work environment sounds exciting, this might be the job for you!

What is your role?

As a Data Scientist, you will be responsible for building various models, both mathematical and supervised machine learning. You will be working heavily with geospatial and time-series data to help customers better understand what is happening in their fields, what will likely happen in their fields, and what actions they can take to improve their outcomes. You will also be evaluating the condition and quality of customer data to determine its suitability for our various data products and providing feedback on what they can do to improve their data quality.

Some exposure to adjacent fields such as software engineering, data engineering, and DevOps will also be highly valuable as you will need to deploy models into production and build the necessary data pipelines that your project needs. You will also be responsible for building the QA pipelines that monitor outputs and the deployment of our models. It is not expected that you are an expert in any one of these fields only that you either have had some exposure to them or are willing to learn.

What We Are Looking For?

You do not have to have a degree in Data Science or a specific number of years of working experience to join us! We are open to anyone who can cover a good portion of the below.

  • A highly competent individual who is able to self-manage and thinks creatively to help solve customer problems.

  • Good understanding of Python and popular Python packages such as Numpy, Pandas, Matplotlib, SciPy, and Scikit-learn.

  • Familiarity with geospatial data and time-series data.

  • Ability to statistically evaluate models and feature sets.

  • Familiarity with software engineering practices and tools such as Git.

  • Experience with a cloud computing platform such as AWS.

  • Experience working with relational databases and data lakes.

Interest and experience in:

  • Analytical techniques include feature extraction, dimensionality reduction, data visualization, supervised and unsupervised machine learning, and predictive modeling.

  • Agronomy, soil science, hydrology, weather, food security, climatic change, and abatement.

  • Working with stakeholders to understand a problem, create a solution approach, articulate technical results, and make recommendations to a non-technical audience.

  • Understanding and familiarity with remotely sensed data and the underlying physics.

  • Reading scientific journals and converting research methods into code.