Data Scientist-PLY00379 Working at Cargill is an opportunity to thrive—a place to develop your career to the fullest while engaging in meaningful work that makes a positive impact around the globe. You will be proud to work for a company with a strong history of ethics and a purpose of nourishing people. We offer a diverse, supportive environment where you will grow personally and professionally as you learn from some of the most talented people in your field. With 150 years of experience Cargill provides food, agriculture, financial and industrial products and services to the world. We have 150,000 employees in 70 countries who are committed to feeding the world in a responsible way, reducing environmental impact and improving the communities where we live and work. Learn more at www.cargill.com.
Want to work at the forefront of machine learning and agriculture? Cargill has a significant presence across most supply chains in the agricultural space. With that footprint comes massive amounts of data that can inform us about markets and ways to improve our business practices. This position will be part of a newly formed data science team. You work in a team exploring, connecting and mining internal data sources and will develop data models using algorithms for pattern detection and forecasting. In this position you will be part of a multidisciplinary team of high-level problem solvers who use advanced techniques, such as optimization, machine learning, and statistical analysis, to develop solutions that help deliver significant value to a variety of Cargill's businesses and functions. Candidates will be exposed to a wide spectrum of high visibility projects ranging from sales effectiveness, competitive excellence, operational efficiency, sourcing and procurement, supply-chain optimization to trading and financial analysis.
20% Provide data analytics expertise to a cross-functional project team of database specialists, data scientists and business subject-matter experts to complete project deliverables on time and within budget.
20% Propose approaches and suitable algorithms to analyze and leverage data from existing as well as new data sources.
50% Develop and code models by applying algorithms to large structured as well as unstructured data sets. Develop visualization products to share analysis across a large group of business users.
10% Continuously develop business and technical skills to keep up with new advances in data science and develop new capabilities for Cargill.
- Bachelors degree from an accredited college/university in Computer Science, Computational Linguistics, Statistics, Mathematics, Engineering, Bioinformatics, Physics, Operations Research or related fields
- Minimum 3 years relevant work experience (if Bachelors degree) or 0-3 years relevant work experience (if Masters degree) with a proven track record in driving value in a commercial setting using data science skills.
- Knowledge of various modeling algorithms e.g. Linear, GLMs, trees based models, clustering, PCA, and time series models.
- Proficiency in R (e.g. ggplot2, cluster, dplyr, caret), Python (e.g. pandas, scikit-learn, matplotlib, nltk), Spark - MLlib, H20, or other statistical tools.
- Knowledge of databases, data modeling, data warehousing, and distributed computing frameworks
- SQL skills and experience/knowledge.
- Ability to understand complex and ambiguous business needs and applying the right tools and approaches.
- Must be curious, self-motivating, driven and have a passion for problem solving.
- Collaborative team player.
- Excellent communication skills, both written and verbal.
- Experience developing and testing machine learning and/or statistical projects.
- Strong presentation skills. Ability to present statistical results to lay persons in an easy to understand way.
- Masters degree from an accredited college/university in Business Analytics, Computer Science, Machine Learning, Computational Linguistics, Statistics, Mathematics, Engineering, Bioinformatics, Physics, Operations Research, or related fields.
- Experience in agriculture or commodity businesses.
- Experience with weather and geospatial data.
- Experience in software development environment, Agile, and code management/versioning (e.g. Git).
- Experience working in a cloud environment e.g. Amazon Web Services.
- Experience with Big Data development in Hadoop and Spark frameworks.
- Experience with predictive model deployment, tuning, and performance monitoring
Job Research and Development
Primary Location US-MN-Plymouth
Job Type Standard
Shift Day Job