systems
code system
DataJoint-centered workflows for calcium imaging, electrophysiology, pose estimation, photometry, metadata, and lab-scale reproducibility.
code system
Streaming, decoding, feedback, and orchestration experiments where latency and observability are part of the product surface.
code system
Transformer and representation-learning experiments for neural time series, behavior, and model interpretability.
code system
Fast product prototypes, AI workflows, interfaces, and cloud-backed systems that turn ambiguous ideas into usable tools.
github
Jupyter Notebook
Real-time neural data streaming, processing, classification, and foundation-model experimentation framework.
Python
Modular orchestration layer built on top of NeuroForge for BCI pipeline development.
Mechanistic interpretability tools for neural multi-modal transformers.
Python
System of Agents to generate BCI middleware code.
Jupyter Notebook
DataJoint Element for behavioral analysis with DeepLabCut - contributed improvements.
Jupyter Notebook
DataJoint Element for multi-photon calcium imaging analysis.
Python
DataJoint Element for facial inference and video-derived behavior features with Facemap.
Led a major customer deployment for Harvard/Sabatini Lab involving multimodal neuroscience processing and visualization over ~12TB-scale datasets.
TypeScript
Pet fitness tracking and social platform inspired by Shasta.
Jupyter Notebook
ECoG and EEG deep learning based signal classification package.
DataJoint Element for optogenetic experiments
DataJoint Element for miniscope calcium imaging analysis with CaImAn