Job Description

We are working to harness nature to sustainably feed the planet.  We have discovered a transformational opportunity to improve global crop yield and reduce the use of agricultural chemicals and fertilizers by utilizing the core microbiome inside plants to confer material yield and crop protection benefits across a variety of crops, geographies and stresses.  The challenge and opportunity for us is to gain critical first mover advantages by scaling quickly and effectively (~$1B 2020 revenue.)
The Data Scientist will enable optimal data-driven decision making  and dramatically improving farmers’ outcomes.
The Data Scientist will analyze and model expected crop yield under various scenarios. Using large-scale cloud and machine learning algorithms, the Data Scientist will construct data preprocessing pipelines, predictive models, optimization algorithms, and decision support systems.
Key Outcomes:

• Collect and preprocess IoT-scale data from on-farm and remote monitoring equipment including: yield, farm treatments, irrigation, soils, satellite and drone imagery
• Analyze agricultural data to understand the impact of agronomic decisions on crop health and crop yield.
• Use state-of-the-art machine learning tools to understand crop yields as a function of microbiome, crop, planting conditions, soil, weather, farm treatments, and farm conditions
• Produce compelling and clear visualizations of agronomic and statistical findings.
• Partner closely with Software Development to turn Data Science products into best-in-class end-user applications.

Key Competencies:

• Masters Degree + 2-5 years industry experience in a relevant field such as applied computer science, machine learning, mathematics, statistics, quantitative agronomy, environmental science, applied physics or engineering.
• Outstanding communication skills - Outgoing and enthusiastically enjoys explaining statistical analyses and methods to customers and decision makers throughout the organization.
• Experience in and/or eagerness to learn about agriculture, agronomy, GIS, spatial statistics, plant biology, microbiology, agricultural economics, and the plant microbiome.
• Absolutely high fluency with R and/or Python and Bayesian MCMC tools such as JAGS or STAN, as well as conventional statistical analyses, machine learning, and GIS. Strong ability to produce lucid graphical plots, maps, and highly interactive visualizations.  Experience working in various computational environments, such Linux, ec2, S3, Spark, and H2O. 
• Team player – someone who thrives working in cross functional teams throughout the organization.
• A curious, scientific mind dedicated to teasing apart new results through careful, quantitative analysis joined with sound scientific practice.
• Extremely strong customer focus, seeing growers and agronomists as our key end users, and grower success as our ultimate goal.
• Easily adapts to new types of problems and questions. Flexible to different types of analysis and different stakeholders (e.g. lab science, field trials, commercial team).      
• Experience working in industry and a dedication to Data Science performed in an industrial setting.
• Deep understanding of modern Bayesian statistics, ensemble classifiers, regression algorithms, as well as off the shelf machine learning techniques. Experience with model validation and evaluation, and data imputation.       
• Familiarity with SQL as well as NoSQL columnar databases. Experience with MILP, combinatorial optimization, metaheuristics, and other types of optimization are an added advantage.
• Experience with agronomy or ecology work including modeling, forecasting, decision support, and optimization