Software × AI × LanguagesDefense × History × Philosophy
I’m a software engineer in Boston. I work on Wheelbase at Hime, and outside of that I build Grammario and Lociros, two tools for language learners.
Explore my work
01 — Selected work
Auction intelligence, inventory, and recon for used-car dealers. Hybrid vector search ranks every auction car against real inventory gaps; a governed AI assistant runs the rest.
TypeScript · React · TanStack Start · tRPC · Go
Graded readers where A2 is actually A2. Every passage is checked by a morphological analyzer before you read it.
Next.js · FastAPI · Sudachi · CAMeL Tools · spaCy
Click a sentence. See the structure. Universal Dependencies first, AI explanation second.
spaCy · Stanza · FastAPI · Next.js · Supabase
02 — Approach
With AI features I try to get the structure right before involving a model. In Grammario a parser finds the grammar and the LLM only explains it. In Lociros a morphological analyzer checks each generated passage against its level. In Wheelbase the assistant can write SQL, but only inside a restricted Postgres function, and destructive changes need approval. Models are useful but make mistakes, so I add checks where a mistake would matter.
Most of my work spans the stack: database schemas and their security policies, search and retrieval, model calls, APIs, and the interface on top. Two changes I was happy with: rewriting Wheelbase's backend in Go cut database load by more than 80%, and running Grammario's analysis steps in parallel brought a nine-second wait down to about four.
80%+
less database load
~217
tRPC procedures
0
external API calls per VIN decode
60%
faster translation turnaround
03 — Writings
