Sr. Data Scientist

OVERVIEW

Reporting to the VP of R&D, the Senior Data Scientist will serve as a high-level technical contributor within the R&D group, leading the design, development, validation, and implementation of advanced artificial intelligence (AI), machine learning, and data science solutions that improve sugarcane research and operational decision-making. This role is intended for a highly capable professional with graduate-level training, who can translate complex agricultural and industrial problems into scalable analytics products, predictive models, and decision-support tools.

The position will focus on developing and applying AI-driven solutions across sugarcane breeding, crop nutrition, crop health, agronomy, field experimentation, harvesting, logistics, and related industrial systems. The individual will work closely with scientists, field teams, operations personnel, engineers, and external technology partners to identify opportunities, structure data assets, prototype and test models, validate outputs under real-world conditions, and support adoption of new tools that improve productivity, efficiency, and research insight.

This role requires both scientific rigor and practical execution, including hands‑on engagement with field and mill data, geospatial information, remote sensing platforms, sensor technologies, and modern machine learning workflows.

• Lead the identification, definition, and prioritization of AI, analytics, and digital opportunities that can improve sugarcane research, crop management, resource use efficiency, operational performance, and decision quality across the R&D function.
• Design, develop, test, and refine advanced machine learning, statistical, optimization, computer vision, time‑series, and predictive models using data from field trials, laboratory analyses, farm operations, remote sensing platforms, weather systems, equipment, and business records.
• Build data pipelines, modeling workflows, and reproducible analytical processes that integrate multiple data sources into reliable, usable, and well‑documented datasets for research and operational applications.
• Develop AI‑enabled tools and decision‑support solutions for applications such as yield prediction, variety performance analysis, crop nutrition recommendations, irrigation and stress monitoring, disease and pest detection, image‑based scouting, harvest planning, logistics optimization, and mill process improvement.
• Apply geospatial analytics, GIS, drone imagery, satellite imagery, proximal sensing, and other digital agriculture technologies to evaluate spatial variation, monitor crop status, and generate actionable insights for research and operational teams.
• Establish appropriate model development standards, including experimental design, feature engineering, validation protocols, error analysis, performance benchmarking, explainability, and continuous improvement of model quality.
• Translate technical findings into clear recommendations, dashboards, reports, visualizations, and presentations that support scientific interpretation, operational decisions, and leadership discussions.
• Partner closely with operations teams and R&D scientists to understand workflows, define success metrics, validate outputs, and ensure that analytical tools solve practical business and research problems.
• Support data governance and data quality by establishing clear documentation for data sources, assumptions, transformations, metadata, code, models, and decision rules, ensuring analytical work can be audited, repeated, and maintained over time.
• Collaborate with internal and external technology providers, universities, startups, and vendors to evaluate emerging AI platforms, sensing technologies, and…