We are seeking a highly motivated Postdoctoral Appointee with a strong background AI/ML specifically in the development and application of Large Language Models (LLMs) tailored for scientific use cases. This position is focused on advancing the capabilities of LLMs to address complex problems within specific scientific domains, with an emphasis on climate risk assessment and analysis.

As part of a multidisciplinary team, the Postdoctoral Appointee will work at the intersection of AI/ML, climate science, and high-performance computing. The candidate will develop LLMs specifically designed to understand, process, and analyze scientific data specifically related to climate risks, including extreme weather events, long-term environmental changes, and their impact on infrastructure and ecosystems.

This role requires not only expertise in LLMs and machine learning but also an understanding of the unique challenges posed by scientific data, which often includes large-scale numerical datasets, complex simulations, and multimodal information. This position offers the opportunity to work with some of the world’s most advanced computing resources, including Exascale supercomputers, and to collaborate with leading experts across a range of disciplines. Those who are passionate about using cutting-edge AI to address some of the most critical challenges facing our planet are encouraged to apply.

Key Responsibilities:

• Optimize Retrieval-Augmented Generation (RAG) techniques to improve the relevance and contextual accuracy of LLM-generated content.
• Explore and apply multimodal LLMs capable of effectively processing and integrating scientific data from diverse sources, including numerical tables, text, and images.
• Design and implement LLM guardrails to enhance the reliability and accuracy of model outputs in scientific applications.
• Develop and refine automatic evaluation techniques that enable the continuous assessment of LLM performance, particularly in terms of accuracy, relevance, and robustness in scientific contexts.
• Implement conformal prediction and uncertainty quantification techniques to provide reliable risk assessments and uncertainty estimates in LLM applications.
• Present research findings at national and international conferences.

Position Requirements

• Recently completed Ph.D. (typically within the last 0-5 years, or to be awarded in 2024) in Computer Science, Applied Mathematics, or a closely related field.
• Strong programming skills in Python, or other relevant languages used in AI/ML.
• Significant knowledge in machine learning (ML) and applied mathematics.
• Ability to conduct independent research and demonstrated publication record in peer-reviewed conferences and journals.
• Innovative thinking and problem-solving skills in tackling complex scientific challenges.
• Collaborative skills include working well with other scientists, divisions, laboratories, and universities.
• Effective oral and written communication skills with all levels of the organization.
• Ability to model Argonne's core values of impact, respect, safety, integrity, and teamwork.

Desired skills and experience:

• Experience in large language models and their applications in scientific domains.
• Expertise in developing and using machine learning potentials for climate risk analysis and prediction.

Job Family

Job Profile

Worker Type

Time Type