U Jin Seah

I’m a product engineer based in New York.

I ship spatial and business intelligence end-to-end, across model orchestration, computer vision, and generative interfaces.

Software is learning to see. Models are reasoning about space, making decisions on real-world data, and industries are being rebuilt around them.

I’ve been building from inside that shift: an infinite-canvas platform orchestrating 30+ generative models; LLM features turning natural language into structured spatial programs for ~1,800 designers; and an agent pipeline that reads floor plans and returns structured geometry.

Selected work

Talk to a Building

(

Text-to-SQL

Gemini 2.5 Flash

iTwin.js

)

Floor Plan Raster to Vector

(

SAM 2

GeoJSON

React

)

Agentic Image Validation Loop

(

Python

OpenCV

Google ADK

)

Brief to Spatial Dashboard

(

Next.js

Vercel AI SDK

Tailwind CSS

)

Adaptive Interface Logic

(

Gemini 2.5 Flash

Vercel AI SDK

Prisma

)

Spatial Photos on Canvas

(

tldraw SDK

Gaussian Splatting

WebGL

)

Experience

2025 – Present
Product Engineer – HOK
Shipping agent orchestration, floorplan intelligence, and planning platforms firmwide.
2022 – 2025
Product Manager – Yale Accessibility Services
Automating scheduling-and-assignment, lifting request-fulfillment ~25% YoY.
2023 – 2024
Lead Product Designer – Yale Ventures (Tsai CITY)
Shipped social media app, reaching 4,000+ downloads and 1,500+ MAU at peak.