AI Product Engineer/New York, NY/Open to roles
I build full-stack products with LLMs doing the interesting parts.
About
I write software now. I used to cut film.
Lately that's meant semantic search over thousands of records, LLM agent pipelines, and voice interfaces — plus the analytics to see whether any of it worked.
Before code, I led media teams and edited short films. That taught me pacing and what to cut, which turns out to be most of the job in interface design too.
I'm finishing an MS at Northeastern (4.0) and looking for product engineering work where taste and shipping speed both count.
Languages & Frameworks
AI & Data
Infrastructure & Tools
Craft & Creative
Five roles across AI research, enterprise product, and backend systems.
Jan 2025 — Present
Northeastern University · Center for Transformative Media
Boston, MA
I turn a media-studies lab's scattered archives into something you can actually search. I indexed 1,000+ mobile-gaming titles, then swapped keyword search for Gemini function-calling so researchers can ask questions across games, devices, and publications — which cut lookup time about 70%. A Whisper and ElevenLabs voice interface made it less fiddly still.
Jun 2025 — Present
Northeastern University · Institute for Experiential Robotics
Boston, MA
A 40-lab robotics institute couldn't keep up with its own field, so I built the dashboard that tracks it for them — publications, events, and press across every lab. A Tavily and OpenAI ranking pipeline filters the noise (about 3× better signal), and a Flask scanner with a React review UI handles incremental scans. It cut manual monitoring by roughly 80%.
Jul 2025 — Dec 2025
Bright Horizons
Newton, MA
I owned login and onboarding for a CIAM product millions of people use, where one friction point compounds across every sign-in. By mapping the Okta login journey in Pendo and FullStory and reworking the error prompts with engineering, we cut failed logins about 35% and lifted onboarding completion around 20%.
May 2023 — Aug 2024
Devsinc
San Jose, CA
Backend and ML work on the AWS microservices behind an analytics platform. I added FastAPI alongside Django and reworked the batch-prediction schemas, dropping inference latency from ~500ms to ~50ms, and shipped an LLM content feature that lifted engagement 40%.
Dec 2022 — May 2023
SKAI Worldwide (formerly Bitnine)
Seoul, South Korea
I built tooling and CI for a graph-database UI, making a fiddly SQL/Cypher product behave predictably. Rebuilding the pgAdmin components in React and TypeScript pushed feature adoption up 25%, and GitHub Actions pipelines validating Cypher against PostgreSQL cut regression time about in half.
AI systems, full-stack products, and one from-scratch data structure. Each links to the full write-up.
The people who saw the work up close, across the studio and the product team. Hover a face to read what they said.
More recommendations on the way →
Short films and documentary work. It's where I learned pacing and framing, which I bring back to product.
