This project focuses on developing and benchmarking multi-modal AI agents capable of performing expert-level visual inspections of molecular and crystalline structures. Researchers in chemistry and materials science frequently use visual intuition to identify reactive sites, characterize structural features, and verify complex assemblies. We aim to automate these tasks using state-of-the-art artificial intelligence. The intern will perform a comparative analysis between proprietary frontier models, accessed through Argo and SageAPI, and open-weight alternatives hosted on the ALCF Inference Server. The primary objective is to evaluate how these agents interpret 2D and 3D renderings to identify key chemical features, recognize structural anomalies, and assess the geometric integrity of complex atomic systems. By establishing a performance baseline across these diverse inference platforms, the project will help determine the feasibility of deploying digital lab assistants to accelerate high-throughput scientific workflows.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
Job Type
Full-time
Career Level
Intern
Education Level
No Education Listed
Number of Employees
1,001-5,000 employees