Work

Systems, not just demos.

I care about the full loop: framing the problem, building the model, measuring what matters, and making the result useful to people.

01

Applied AI

Language systems that survive real product constraints

Model quality, inference efficiency, calibration, and maintainable experimentation treated as one engineering problem.

Explore source
02

Research

Graph-based reasoning for long-document summarization

Published work exploring graph attention, selection, and generation for abstractive summarization.

Explore source
03

Founder work

RadarCX — practical AI assistance for demanding work

A product-building practice across AI systems, planning, human control, and trustworthy interaction.

Explore source