Speaker
Description
Real-time multi-messenger astrophysics is as much a computing problem as a telescope problem. The same event can trigger gravitational-wave, neutrino, radio, and optical alerts within seconds, but the science only happens if the infrastructure can carry, filter, and join those streams fast enough to act on them. I work on three of these systems: ANTARES, which ingests and classifies Rubin's ~10 million optical alerts a night; SCIMMA's Kafka-based Hopskotch platform, which carries the full LIGO-Virgo-KAGRA gravitational-wave alert stream and rapidly triggers Rubin to follow up the most promising events as targets of opportunity; and the throughput-bound, federated analysis coordination behind LSST DESC cosmology. The classification and prioritization at the center of all three will increasingly run on foundation models we build at the NSF-Simons SkAI Institute, trained across multi-survey, multi-modal data (light curves, images, and spectra). The hard parts — real-time inference at scale, latency- and reliability-critical alert delivery, federated data movement, and GPU-scale model training — are where we could use this community's help.