I'm Chief AI Architect for Global Finance at Caterpillar, where I architect complex enterprise agentic systems and modern AI-first user interfaces, and I keep making interactive experiments on the side. Before that I led R&D at BrainCo, a brain-computer interface startup, which I joined after a spell at Apple as a machine learning research intern. I came to industry from a postdoc at MIT, where I had also done my PhD, both in the Media Lab's Fluid Interfaces Group, working on brain-computer interfaces, AI, complex systems, affective computing, and tools that extend human memory and attention. Earlier I did my master's in applied mathematics at Oxford, and before any of it I studied electrical and biomedical engineering at Tehran Polytechnique. I'm passionate about the intersection of software, design, and intelligence, both artificial and biological.
Experience
Education
Skills
Honours
Earlier Work
Brain decoding using BigGAN and MusicVAE to generate naturalistic neurofeedback stimuli.
Using affective signals to condense 16 hours of body-cam footage into a 15-minute daily recap.
Self-supervised EEG-based user identification at scale, surpassing prior 157-subject limits.
Sonification of electrophysiological signals — turning EEG, ECG, and EMG into sound.
Open-source tool for in-depth visual analysis of multi-channel time-domain neural recordings.
A flexible deep learning building block that combines skip connections and normalization in one layer.
An intelligent interface that builds a personal knowledge graph through natural conversation.
VR visualization of the Twitter social graph during the 2016 U.S. Presidential Election.
A tool for navigating personal memories to support people living with dementia.
AI-driven mapping of the 2016 election public sphere — where machine intelligence meets political journalism.
Contrastive learning of representations for EEG and other time-series data, without labels.
Testing how spatial memory holds up on a parabolic flight, once the sense of up is gone.
A knowledge graph of food, linking how we talk and learn about it to what it actually contains.
A talk on the Electome from the Laboratory for Social Machines, built with Twitter and Knight Foundation.
An interface with the soul of a city. First place and the Bill Mitchell Design Award at Make Me++.
