Postdoctoral Research Fellow

Key Responsibilities

• Collaborate with faculty to design, implement, and support sustainability-related research projects requiring advanced data analytics.
• Develop and maintain a centralized platform for the Pan-Amazon Evidence and Action Hub that hosts diverse and harmonized sustainability-related datasets, including environmental, socioeconomic, cultural, and geospatial data.
• Design and implement reproducible pipelines that ingest, clean, and harmonize fragmented data from remote sensing, survey, census, administrative, and citizen science sources into coherent, analysis-ready datasets with documented lineage and quality metrics.
• Create tools and interfaces (APIs, catalogs, dashboards, or reproducible workflows) that make Hub data discoverable and usable by faculty, students, and partner organizations with varying technical capacity.
• Explore applications of AI methods, including large language models and natural language processing, for extracting structured information from unstructured sources (e.g., reports, policy documents, gray literature, or citizen science observations).
• Apply advanced statistical, machine learning, and AI techniques to analyze complex datasets and uncover actionable insights.
• Co-author and support high-impact, interdisciplinary research publications in leading sustainability and environmental science journals.
• Engage in collaborative grant writing and proposal development to sustain and expand the cohort’s research initiatives.

Qualifications

• Ph.D. (in hand by the starting date) in Data Science, Computer Science, Statistics, Geography, Environmental Science, or a related field with a strong computational focus.
• Strong data engineering skills in Python and/or R, preferably in building reusable data pipelines rather than one-off analysis scripts.
• Demonstrated experience harmonizing heterogeneous data sources: reconciling inconsistent schemas, units, geographies, and vintages across datasets such as remote sensing products, surveys, censuses, and administrative records, and documenting those decisions in a reproducible way.
• Expertise in geospatial data, including working across raster and vector formats, coordinate reference systems, and spatial aggregation or interpolation across mismatched administrative and ecological units.
• An interest or experience in using machine learning or AI tools with environmental or socioeconomic data.
• Excellent communication skills and the ability to translate technical infrastructure decisions for collaborators from a wide range of disciplines.