About Me
Physicist (Ph.D.) with 10+ years building ML pipelines, Bayesian inference frameworks, and statistical models for large-scale physics data — galaxy surveys, gravitational lensing, dark energy, and cosmological simulations. Expertise in PyTorch, normalizing flows, diffusion models, vision transformers, and simulation-based inference. 25 peer-reviewed papers with 1,100+ citations. Transitioning to industry roles in AI/ML, data science, and quantitative finance.
I'm currently a Postdoctoral Research Fellow at the MIT Center for Theoretical Physics, where I develop machine learning methods for cosmological data analysis. My work spans normalizing flows for Bayesian parameter estimation, simulation-based inference for galaxy surveys (DESI, BOSS, SDSS), and diffusion models for scientific imaging.
During my PhD at Brown University, I built deep learning pipelines (CNNs, unsupervised methods, domain adaptation) to detect dark matter signatures in gravitational lensing images, and created open-source Boltzmann solvers that have become standard tools in the cosmology community. I also spent a summer at Microsoft Research collaborating with Jaron Lanier and Lee Smolin.
I've led cross-institutional research teams spanning MIT, Harvard, Brown, Cambridge, Edinburgh, and others, and mentored 37+ students. I leverage AI-augmented development tools (LLM coding agents) daily to accelerate research and software development — this website was built entirely with Claude Code. I'm now looking to bring this experience to industry — particularly ML engineering, data science, or quantitative research roles.
Skills & Technologies
ML & Deep Learning
Statistics & Inference
Languages & Computing
Tools & Software
Career Timeline
Postdoctoral Research Fellow
MIT Center for Theoretical Physics
Developing normalizing flow models for Bayesian inference, simulation-based inference pipelines for DESI/BOSS/SDSS galaxy surveys, conditional diffusion models and vision transformers for scientific imaging, and an LLM-driven framework for automated scientific model-building (NeurIPS 2025).
Research Intern
Microsoft Research
Collaborated with Jaron Lanier and Lee Smolin on research at the interface of theoretical physics, machine learning, and computer science. Contributed to "The Autodidactic Universe" (2021).
Ph.D. Physics
Brown University
Advisor: Prof. Stephon Alexander. Built deep learning pipelines for dark matter detection from gravitational lensing images. Created open-source packages (NPTFit-Sim, CLASS_EDE, CLASS_KINETIC, DeepLense). Key papers garnered 400+ combined citations.
ML4Sci Mentor, Google Summer of Code
Mentored 25+ students across 6 years developing ML algorithms for scientific image analysis. Student projects resulted in 20+ publications and 16 NeurIPS workshop acceptances.
Instructor, Summer@Brown
Brown University
Designed and taught a 3-week introduction to astrophysics and cosmology for high school students.
Sc.M. Physics
Brown University
Master's research in theoretical cosmology and early dark energy models.
NREIP Research Intern
U.S. Naval Research Laboratory
Developed Python-based automation tools for the Fermi Large Area Telescope (Fermi-LAT), streamlining processing of terabytes of high-energy astrophysical data.
B.S. Astronomy & Astrophysics; B.S. Physics
The Pennsylvania State University
Schreyer Honors Scholar. Graduated cum laude with Honors in dual degrees.