Remote Sensing Data Scientist

Company Description

About Syngenta 

At Syngenta Seeds Field Crops, we're shaping the future of agriculture and empowering farmers to meet the ever-growing demand for food and fuel. We’re a global Ag Tech powerhouse, headquartered in the United States, with passionate, local experts collaborating with farmers to deliver solutions that create market opportunities.  We unite precision breeding, advanced biotechnology trait choice, and digital platforms for unmatched in-field performance.  Our seeds help mitigate risks such as disease, insect, weed, and extreme weather pressures, all while promoting sustainable farming practices that protect and enhance our planet. Join our mission of revolutionizing food security and transforming agriculture. 

Job Description

At Syngenta, we are building the most collaborative and trusted team in agriculture to provide leading seeds innovations that enhance the prosperity of farmers worldwide. Our Digital Germplasm Development Team is seeking a motivated Remote Sensing Data Scientist who will be instrumental in revolutionizing how we leverage geospatial intelligence to accelerate breeding programs and bring superior seeds to market faster.

In this role, you will support the development and deployment of computer vision solutions that extract digital traits from multi-modal plant imagery to accelerate breeding decisions and enable self-supervised learning products. Drive the strategic vision for scalable phenomics platforms that transform raw imagery from drones, ground-based sensors, and mobile devices into actionable breeding insights and AI-powered identification tools for internal and external users. As an individual contributor, you'll combine technical excellence with scientific rigor to transform raw imagery into actionable breeding intelligence.

This is an opportunity to apply cutting-edge remote sensing and AI technologies to solve real-world agricultural challenges on a global scale.

Accountabilities:

• Design and maintain scalable, production-grade remote sensing data pipelines that ingest, process, and manage multi-source geospatial imagery supporting global breeding operations.
• Develop and operate automated image preprocessing and quality-control workflows to reliably transform raw imagery into analysis-ready data.
• Build and deploy machine learning and computer vision solutions that extract breeding-relevant insights from large-scale, multi-temporal imagery datasets.
• Integrate multi-sensor data sources (satellite, drone, ground-based, and environmental data) into unified analytical frameworks enabling advanced spatial analysis.
• Deliver time-series and geo-temporal analyses that characterize crop growth, phenology, and genotype-by-environment interactions across global trial networks.
• Develop embedding-based approaches that learn rich representations from imagery for downstream prediction tasks (yield, stress, disease, trait values).
• Leverage foundation models and transfer learning (vision transformers, self-supervised learning, geospatial foundation models) to create robust, generalizable solutions across crops and environments.
• Partner closely with data engineering and IT teams to design and implement a unified enterprise geospatial data platform and enable efficient spatial querying at scale.
• Collaborate effectively with relevant subject matter experts and data science colleagues to ensure solutions are scientifically sound, reusable, and aligned with business priorities.

Qualifications

PLEASE NOTE: Candidates must be legally authorized to work in the United States on a permanent basis without requiring current or future sponsorship (which also refers to OPT/CPT and H-1B visas).

• Master's or Doctoral degree in Remote Sensing, Geosciences, Agricultural Engineering, Ecology, or a related field.
• 3+ years of hands-on experience with remote sensing imagery and geospatial data in research or production environments, such as multi-sensor data (multispectral, hyperspectral, SAR, thermal, LiDAR).
• Advanced Python programming with geospatial libraries (GDAL, Rasterio, GeoPandas, Xarray), ML/DL frameworks (PyTorch, TensorFlow, scikit-learn), and cloud platforms (AWS, GCP, Azure).
• Proven ability to build and deploy production-grade geospatial data pipelines and scalable ML/computer vision models for segmentation, classification, and object detection on large imagery datasets.
• Experience with advanced ML techniques such as transfer learning, foundation models, self-supervised learning, and embedding-based approaches – particularly in limited-labeled-data scenarios.
• Software development fundamentals – version control (Git), containerization (Docker), CI/CD workflows, and geospatial data management best practices.