Postdoctoral Scholar in Natural Language Processing and Mammalian Evolution

University of Florida • Gainesville, FL

1d

About The Position

This project seeks to unlock hidden data within centuries of field observations, dietary studies, and taxonomic accounts about what mammals eat. These data are currently embedded in unstructured text across thousands of publications with inconsistent terminology. The project will develop a human-in-the-loop AI pipeline using LLMs to extract consumer-food relationships from scientific literature at scale and convert qualitative descriptions into standardized ordinal dietary rankings for evolutionary biology research. The central hypothesis is that the published literature contains a vast reservoir of latent dietary information that can be systematically transformed into reproducible quantitative datasets. Unlike existing mammalian diet databases that rely on manual expert curation, this project will combine AI-assisted information extraction with expert validation to create high-resolution dietary datasets spanning the mammalian tree at an unprecedented scale. The Postdoctoral Researcher will lead the development of the dietary ranking framework and database construction. They will collaborate with an interdisciplinary team of ecologists, biodiversity scientists, and AI researchers, contributing to the development and evaluation of LLM-based information extraction methods, analyzing large-scale dietary datasets, and advancing computational approaches for ecological synthesis. The role involves independent and collaborative research, publishing in leading journals, contributing to grant proposals, mentoring students, and shaping the future of this interdisciplinary program. The position offers excellent opportunities to gain expertise in AI for biodiversity science, build a strong publication record, and develop a collaborative network for an academic or research career. This is a one-year position, renewable for up to three years based on performance and funding availability.

Requirements

• Ph.D. in natural language processing, computer science, data science, ecology, evolutionary biology, biodiversity informatics, bioinformatics, or a closely related field, completed or expected to be completed before the start date.
• Demonstrated research experience in at least one of the following areas: Natural language processing, large language models (LLMs), information extraction, or machine learning; or Ecology, evolutionary biology, biodiversity informatics, or similar, with a focus on large-scale, quantitative research.
• Strong programming skills in Python and experience with scientific computing, data processing, and reproducible research workflows.
• Experience designing, implementing, and evaluating computational methods or data analysis pipelines.
• Excellent written and oral communication skills, with evidence of peer-reviewed publications or a strong publication trajectory.
• Ability to work independently while contributing effectively to an interdisciplinary, collaborative research team.

Nice To Haves

• Experience with modern NLP and LLM techniques, including transformer models, prompting strategies, named entity recognition, relation extraction, or information extraction from scientific literature.
• Experience working with biodiversity, ecological, evolutionary, or biological trait datasets.
• Familiarity with annotation workflows, corpus development, or evaluation of machine learning models.
• Experience with statistical analysis, multivariate methods, or comparative and phylogenetic analyses.
• Experience using high-performance computing (HPC), cloud computing, or large-scale machine learning workflows.
• Familiarity with open science, FAIR data principles, and research data management.
• Experience mentoring undergraduate or graduate students and contributing to collaborative research projects.

Responsibilities

• Play a leading role in developing the dietary ranking framework and constructing the resulting database.
• Contribute to the development and evaluation of LLM-based information extraction methods.
• Analyze large-scale dietary datasets.
• Help advance computational approaches for ecological synthesis.
• Conduct independent and collaborative research.
• Publish in leading scientific journals.
• Contribute to grant proposals.
• Mentor graduate and undergraduate students.
• Help shape the future direction of this growing interdisciplinary research program.

Benefits

• Excellent opportunities to develop expertise in AI for biodiversity science.
• Building a strong publication record and collaborative network for an academic or research career.

What This Job Offers

• Job Type: Full-time
• Career Level: Entry Level
• Education Level: Ph.D. or professional degree