Malden, Massachusetts, United States
Formerly a member of the LIGO Scientific Collaboration where I worked on gravitational waves. My research involved signal analysis, statistical analysis, Bayesian inference, and working on novel machine learning uses that aim to assist, rather than replace, current computational methods. Publications: https://orcid.org/0000-0002-7797-7683
Designed and implemented software that proved the effectiveness of novel waveforms used to search for exotic objects (objects which are not black holes or neutron stars). Containerized, parallelized, and performed large scale computations across high performance computing (HPC) clusters. Analytically derived and coded folded kernels for a statistical inference framework, iDQ, to better classify non-Gaussian noise artifacts in LIGO’s real-time timeseries data. Performing research that involves signal analysis, statistical analysis, Bayesian inference, and working on novel machine learning uses that aim to assist, rather than replace, current computational methods. Member of the LIGO Scientific Collaboration and the GstLAL (a low latency Bayesian driven data analysis pipeline) group.
Led a project that improved gravitational wave (GW) search sensitivity by designing a method that utilizes streaming classification and detector sensor data. Worked on a machine learning model that aims to increase the performance of low latency parameter estimation through the use of waveform interpolation. Explored physics informed neural nets (PINNs) and ultimately accelerated our gravitational wave matched filter calculations.
Proton radiography modeling and simulations that utilized high performance computing (HPC) techniques. Converted modeling code to be CUDA compatible and developed a Qt phone application.