ResAlign AI
A career copilot for fit, preparedness, and alignment—not another apply-to-everything button.
In the wildCase study
Projects
Systems with a question behind them.
Product, infrastructure, and research engineering—selected work with the context left in.
HarnessBox
Sandbox and harness primitives for coding agents. Zero dependencies, on purpose.
BuildingCase study
agentic-rag
Multimodal agentic RAG with a real evaluation harness. “It felt pretty good” is not a metric.
Open sourceCase study
CheckThat
Noisy social posts to concise, checkable claims—class project to paper to pip install.
PublishedCase study
Rational Neural Nets
Teaching neural networks to rationalize sentiment with human annotations and LIME.
ArchiveCase study