2026-11-03 –, Banquet Hall
Building and optimizing High-Performance Computing (HPC) pipelines for next-generation radio telescopes (e.g., SKA) presents immense software engineering challenges. We present a novel approach using continuous "Loop Engineering" driven by specialized Large Language Model (LLM) agents to refactor a radio interferometry imaging codebase (RICK). By deploying distinct AI personas—such as an HPC/MPI specialist, a GPU-porting engineer, and a domain-specific radio astronomer—we automated complex architectural upgrades. Operating sequentially to prevent code conflicts, these agents successfully aligned scientific outputs with industry standards (WSClean) within a strict 1% tolerance, guaranteed MPI scale invariance, and optimized OpenMP GPU memory traffic. We discuss the efficacy of agent-driven automated development, the technique of prompt cross-validation across different LLM engines to debug complex FITS WCS metadata, and the paradigm shift from manual coding to managing autonomous AI engineering loops in astronomical software development.
The pipeline used as a benchmark for this experiment (RICK) is a highly modular C++ computational engine designed for high-resolution imaging and deconvolution of massive radio astronomy datasets. The autonomous multi-agent framework allowed an engineer transitioning from traditional HPC to AI-driven workflows to address both low-level parallel optimizations (MPI/GPU) and high-level astrophysics validation (such as WCS coordinate systems and flux calibration alignment) within the same development cycle. Crucially, the AI infrastructure was also leveraged to explore future hardware horizons, evaluating how the code's modular structure could be prepared for the upcoming computational paradigm shifts.
Dr. Giovanni Lacopo serves as a Technological Researcher specializing in software development for the SKA SRCNet. He earned his Master’s degree in Theoretical Physics in 2021, shifting into computational astrophysics for his PhD in Computer Science and Astronomy, which he completed in 2025 with a focus on 'Green HPC and Big-Data analysis with applications in numerical cosmology'. Bridging the gap between physics-driven algorithms and massive scale-out computing, his current research focuses on the synergistic entanglement of HPC workflows and Artificial Intelligence. He is actively pioneering the use of autonomous multi-agent systems to accelerate, refactor, and scientifically validate data processing engines for next-generation astronomical facilities.