You will work collaboratively with interdisciplinary scientists, IT, and engineering professionals across the organization to solve critical problems and answer important questions that drive key decisions for our business. You will foster innovative ideas to produce sophisticated, intelligent optimization solutions and predictive models.
Works on a team as an individual contributor collaborating with other Data Scientist and subject matter experts with business and crop science experts.
Major Tasks & Responsibilities
Provide technical contributions in collaborative environment to accelerate our efforts on building an analytics-driven product pipeline.
Develop and deploy new solutions based on predictive and prescriptive modeling utilizing a wide range of field observations and environmental data (weather, soil, remote imagery), to improve field operations and enable better decision making.
Build cross-functional relationships to collaboratively partner with the business and effectively network within our valued and highly collaborative Data Science Community.
Use advanced mathematical/ statistical models, machine learning algorithms, and strong business acumen to deliver insights, recommendations, and solutions.
Develop sustainable, consumable, accurate, and impactful reporting on model inputs, model outputs, observed outputs, business impact, and key performance indicators.
Present compelling, validated stories to all levels of organization, including peers, senior management, and internal customers to create both strategic and operational changes in business
Qualifications and skills.
Masters degree with 2+ years of experience or PhD.
Educational preparation or applied experience in at least one of the following areas: Machine Learning, Computer Science, Mathematics, Statistics or other closely related quantitative discipline. Candidates with demonstrated experience in applying machine learning to environmental modeling, crop modeling, epidemiology, or other modeling and interpretation of found, open systems data preferred (but not required).
Strong programming experience in Python, R, or another high-level programming language, ideally with working with machine learning and statistical modules/ packages. Demonstrated experience in reinforcement learning a plus.
Strong computer development skills, with demonstrated experience in collaborative coding and version control (GIT) and ability to write clear, well commented, and organized code.
Experience in Agile project management and/ or willingness to learn
Experience in building models, including data extraction and cleaning, feature selection and engineering, and model selection/ validation
Strong sense of ownership to deliver valuable analysis through acquisition and application of domain knowledge; motivated to develop and work from a strong understanding of our business and the science required to execute it.
Strong communication competencies to include presentations and delivery of complex quantitative analyses in a clear, concise, and actionable manner to extended team and small groups of key stakeholders.
Working on new machine learning methods (e.g. Bayesian Methods, GCN, Spherical CNNs, GAN, Unsupervised Learning, Distributed Learning and others) and methods for gaining insights from these models (shapely, partial dependence, etc.)
Design and implementation of artificial neural networks
Working closely with product management to define product strategy and roadmap
Creation of innovative products supported by prototypes, scientific publications and patent applications