Data Scientist

Bunge•Chesterfield, MO

2d•Onsite

About The Position

The Data Scientist will be an integral part of the Bunge Economic Analysis team, leveraging advanced statistical modeling, econometrics, and machine learning to analyze vast internal and external datasets. This role is crucial for developing sophisticated predictive models that inform our understanding and forecasting of global commodity market dynamics, including crop production, pricing trends, and customer behavior, thereby advancing our economic research functions worldwide.

Requirements

Minimum MS degree in Economics, Agricultural Economics, Statistics, Computer Science, Quantitative Finance, Business Analytics, or a closely related quantitative field.
Minimum 2-year of professional experience in a Data Scientist or similar quantitative role, preferably within an economic analysis, commodity trading, financial services, or agribusiness environment.
Expert proficiency in Python (e.g., pandas, NumPy, scikit-learn, statsmodels, TensorFlow) for data manipulation, statistical analysis, machine learning, and data visualization.
Strong SQL skills for data extraction, manipulation, and analysis from relational and non-relational databases.
Solid understanding of statistical inference, econometric modeling (e.g., time series analysis, causal inference), and machine learning algorithms (e.g., regression, classification, clustering, tree-based models).
Demonstrated ability to frame complex problems, design analytical solutions, and extract meaningful insights from large datasets.
Excellent communication and presentation skills with the ability to explain complex concepts or methods in a precise and clear manner.
Detail-oriented, proactive, self-motivated, build work relationships, and able to work both independently and collaboratively in a fast-paced, dynamic global environment.

Nice To Haves

5+ years of industry work experience in Data Science fields.
Experience with geospatial data analysis, remote sensing, satellite imagery processing and deep learning for statistical modeling.
Experience with big data technologies and cloud-based data platforms and products (e.g., Google Cloud Platform, AWS).
Familiarity with MLOps practices for deploying, monitoring, and maintaining machine learning models in production.
Specific knowledge of agricultural commodity markets (e.g., grains, oilseeds, biofuels), agronomics, etc.

Responsibilities

Collaborate effectively within cross-functional teams, including economists, market analysts, data engineers, and business leaders, to translate complex business challenges into solvable data science problems.
Translate complex business problems into data-driven analytics and machine learning tasks, then design, develop, and swiftly deploy high-performance, resilient predictive models using a range of machine learning, statistical, and econometric techniques.
Design and implement advanced analytical strategies and algorithms to extract, analyze, and leverage diverse data sources. Critically assess the effectiveness, accuracy, and suitability of various data inputs for global economic models.
Rigorously monitor, evaluate, and refine the performance of deployed machine learning solutions to ensure sustained accuracy and measurable business impact.
Clearly and effectively communicate complex analytical findings, model insights, and strategic recommendations to diverse audiences, including senior leadership, traders, and business units, supporting informed decision-making and global risk management.