Extract insights from the agronomic, soil and environmental data we collect on our customer’s enterprises. As part of the Advanced Agrilytics data science team, your main responsibility will be to develop quantitative solutions and help support new techniques to address challenges in digital agriculture using large datasets.
The Data Scientist will translate clients' data requirements into technical development encompassing data profiling, metadata enrichment, provenance and lineage, exploration, statistical analysis, data mining, machine learning, visualization, modeling, and reporting.
Provide reports, analyses, processes and visualizations through the various company life cycles.
Provide consulting and assistance to agronomists in the effective understanding and use of analytical outcomes and tools.
Proposing new ideas and novel solutions that do not follow conventional thinking or approaches.
Conduct written and verbal presentation to share insights and recommendations to audiences of varying levels of technical sophistication.
Establish procedures for the application of basic machine learning algorithms to agronomic and environmental data.
In collaboration with the Engineering team, develop processes to implement quantitative solutions.
Develop and support quantitative solutions and related documentation.
Extending data resources with third party sources of information when needed.
Lead and self-starter who can own complex projects from start to finish
Identify development needs in order to improve and streamline operations.
Support the Chief Science Officer in processes such as building a robust analytics system to include digital agriculture components. For instance, crop, soil, and water management, and other relevant strategies or duties based on the needs of the Data Science Office.
Leading learning relationships between team members
Skills and Competencies
A complete Master’s or Ph.D. degree in Mathematics, Applied Mathematics, Statistics, Applied Statistics, Machine Learning, Data Science, Computer Engineering, or Computer Science
A degree in a related field (e.g., Computer Information Systems, Engineering, Statistics)
10+ years of professional work experience
10+ years of relevant industry experience with statistical tools such as SPSS, SAS, Stata, and/or other relevant predictive and modeling software
8+ of relevant industry experience with common data science toolkits such as R, Anaconda Python, Julia, and Apache MADlib
6+ years of relevant industry experience with data visualization tools and graphical libraries such as Tableau, Business Object, Plotly, D3.js, GGplot, etc.
Strong background in statistics methodology and the ability to infer causal relationships. Have taken such as probability, random variables, design of experiments, statistical inference, and multivariate analysis
Excellent applied statistics skills, such as a complete understanding of probabilistic distributions, ability to perform parametric and non-parametric statistical testing, regression analysis, and latent variable models.
Strong background in computer and programing skills. Have taken such as algorithms, programming, data structures, data mining, artificial intelligence, machine learning, and pattern recognition
Excellent understanding (assumptions and drawbacks) of statical models and machine learning algorithms, such as generalized linear models, k-NN, Naive Bayes, tree-based methods, mixture models, SVM, random forests, neural networks, etc.
Knowledge of advanced statistical and data mining techniques (e.g. time series, structural equation modeling, reliability analysis, stochastic models, and ensemble learning) and their proper usage, and experience with applications such as SPSS and SAS to include integrating R and/or Python
Data mining using state-of-the-art methods on large spatio-temporal datasets derived from agricultural production systems.
Experience in working with large-scale spatial and temporal data.
Experience with ArcGIS or other geographic information systems (GIS) platform would be beneficial
Provide successful cases of data analysis such as peer review papers, github project, or any other related result published on analytical and ML content platforms
November 4, 2020