AI/ML for science & applied research. I’m Head of AI at DreamStreet. Before that I was Senior Principal Research Scientist at Dream Sports / Dream11, where I led applied AI research and a research partnership with Columbia University. My research interest is in learning systems that do science reliably, with a strong inclination towards computational biology.
This site is where I write up the engineering behind that work - mostly field reports on HPC, applied ML, and the measurements behind the results.
Python vs Rust: k-means at scale Side-by-side performance comparison of k-means clustering implementations in Python (NumPy / scikit-learn) and Rust, on synthetic benchmark datasets.GitHub ↗
SimuCell3D: HPC tissue mechanics in C++ Performance-oriented fork of an ETH-developed C++ framework for 3D tissue mechanics at subcellular resolution. On eight cores v2.1.0 grows the benchmark tissue to around 145,000 cells in two days and runs about twice as fast as v1.0 on the cases both versions run.GitHub ↗
Ultrasound Doppler angle from B-mode with deep learning A deep-learning project that reads the Doppler angle from a single grayscale carotid B-mode image. It extends my EMBC 2019 paper with grid pooling on a frozen backbone, Optuna-tuned estimators under two sampling protocols (down to ~2° MAE), and a calibrated clinical evaluation.GitHub ↗
Data Science Docker Environment Opinionated Dockerfile + compose setup for a reproducible Python/R data-science stack: Jupyter, common ML libraries, and a pre-wired notebook server.GitHub ↗