Seminar Title: Argo: From Launch to GenAI-as-a-Service for National Laboratory Operations

Speaker: Matthew Dearing, Enterprise Software Engineer and Technical Lead, Artificial Intelligence, Argonne Initiative, Argonne National Laboratory, Joint Appointment as a CASE Staff At-Large, Department of Computer Science, University of Chicago.

Date: Thursday, October 9, 2025

Time: 1:30 PM-2:30 PM (In-Person)

Location: Hybrid, Bldg. 240, Conference Room 4301

Host: Jeff Larson

Description: Since launching “Argo” in December 2023, Argonne National Laboratory has evolved its generative AI platform from a secure chat interface toward an AI-as-a-Service infrastructure. We present the technical deployment of both the user-facing chat interface and the Argo Gateway API, which provides programmatic LLM access for custom applications. Usage statistics demonstrate growing adoption across science and operations communities. We highlight use cases and published research leveraging Argo, and discuss how centralized service delivery eliminates duplicative development while ensuring consistent data privacy, authentication, and accessibility. We conclude with considerations and challenges specific to national laboratory deployment: managing rapidly evolving model vendors, implementing secure retrieval-augmented generation, and balancing AI agent autonomy with compliance and ethical requirements.

Bio: Matthew Dearing is an enterprise software engineer and Technical Lead for the Artificial Intelligence at Argonne initiative at Argonne National Laboratory with a Joint Appointment as a CASE Staff At-Large in the Department of Computer Science at the University of Chicago. Matthew is also working toward a Ph.D. in Computer Science at the University of Illinois Chicago, where he researches innovative AI approaches to enhance the operations of high-performance computing (HPC).

Please note that the meeting URL for this event can be seen on the cels-seminars website which requires an Argonne login.