Work
Unless stated, projects are designed and built on my own.
Breck

2024-present
A low-code local genAI-powered programming interface that explores the use of LLMs as natural-programming language compiler/translator.
- locally-run code LLM (Qwen2.5-Coder)
- generated code is evaluated in-browser with Wasm
- intermediate pseudocode prioritizes understanding
- low-code node-based programming interface
TypeScript
React (Next.js)
React Flow
CodeMirror
WebAssembly
QuickJS
Pyodide
Dexie
Ollama
Flask
Chronotome

2024-present
An incremental, time-based topic modelling tool and visualizer that shows thematic evolution over time.
- uses embeddings as primary input
- works on both text and image datasets
- incrementally adding data evolves graph structure
- clustering snapshots show thematic evolution
- parallelizes computation in worker threads
TypeScript
Svelte
Three.js
Python
Flask
HuggingFace
PyTorch
hdbscan
OpenAI
Lead Engineer
Catherine Yeh (Research Engineer)
PixMath

2024-present
A prompt-less deterministic image genAI which takes math expressions of images as input, based on prior CV research.
- simple drag-and-drop no-code interface
- job queue dispatches API calls to GPU backend
- uses server-sent events (SSE) for real-time frontend updates
TypeScript
React
pragmatic-dnd
Pocketbase
Go
Flask
PyTorch
Docker
Sememo

2023-present
A vectorDB, RAG and genAI-powered note-taking progressive web app (PWA) for writers to understand themselves. In closed beta.
- auto-identifies connections across notes
- generates tailored consolidation and recommendation using RAG1
- I use it as my daily driver
React (Next.js)
Node.js (Express)
Weaviate
SQLite (Drizzle)
OpenAI
NextAuth
Docker
Real-time Video Networks Research

2024
MIT 6.5820 (Networks) research exploring delay and network probing tradeoffs for real-time video.
- used existing BBR implementation in Linux kernel
- identified optimal probing strategy given constraints
Python
Ubuntu
shell
Mahimahi
Researcher
- Laura Landon (same as above)
- Rohan Menon (same as above)
Naya Timeline

2024
A scheduling feature update enabling drag-and-drop (DnD) interactions and task assignment.
- edit element dates on calendar using DnD
- view task assignees
TypeScript
React
Redux
react-big-calendar
YJS
Lead, Software engineer
Diksha Jaiswal (Designer)
Naya Presentation Generation

2024
A one-click genAI & RAG feature that crafts a presentation using project contextual metadata.
- understands project context and available assets
- produces a pitch-ready Google Slide or .PPTX
- provides options for specified or freeform structure
TypeScript
React
Redux
Node.js (Express)
MongoDB
GCP
OpenAI
Google APIs
GCS
Lead, Software engineer
Krishna Zolpatil (Designer)
Naya GenAI Infrastructure

2024
A system that ingests multiple file types to construct project-specific contextual metadata for downstream genAI and RAG tasks.
- ingests wide range of file and link types into common metadata format
- auto-ingestion of project asset updates
- high throughput via serverless architecture
- fast metadata production by parallelizing API calls
TypeScript
Node.js (Express)
MongoDB
YJS
Python
LangChain
OpenAI
Anthropic
GCS
GCP
Lead, Software engineer
- Vivek H V (CTO)
- Surya Mohan (DevOps)
- Pavankumar Kushnure (Software engineer)
Tobe

2024
An alternate YouTube watcher that prioritizes user attention while adding useful features.
- prioritizes user attention by reducing distraction
- user-customizable settings (e.g. time limits)
- users can curate channels by selecting creators
TypeScript
Next.js (React)
Google APIs
IndexedDB
shad/cn
PixMath CV Research

2024
MIT 6.8300 (CV) research exploring diffusion model latent space navigation using images as input.
- inverted images into CLIP embeddings for arithmetic computation to generate final image
- found formulaic expressions that extract semantics and style
- potential for non-technical users to probe the model (e.g. for bias) – see PixMath
Python
PyTorch
NumPy
OpenCV
HuggingFace
Diffusers
Eye-paratus AR+CV Research

2023
Research exploring projection-based augmented reality (AR) for explainable robot vision (CV).
- combines projection-mapping and real-time object detection for model transparency
Python
Arduino
OpenCV
MediaPipe
Software engineer
Kevin Tang (Lead & Hardware)
Interprexis NLP Research

2023
MIT 6.8610 (NLP) research exploring human-interpretable concepts inside contextual word embeddings.
- used a simple linear classifier to identify embedding axes related to specific concept
- found that concepts are entangled across axes
- identified axes with greater impact on classification
Python
PyTorch
HuggingFace
DistilBERT
pandas
NumPy
OpenAI
Matplotlib
scikit-learn
Researcher
- Catherine Yeh (same as above)
- Joanna Shen (same as above)
- Ziqian Liao (same as above)
PastPort


2022-2023
A location-based AR web app that digitally preserves places that are lost through urban renewal.
- web-based AR, does not require app download
- location-based archival image retrieval
- a DesignSingapore Good Design Research grant project
Svelte
p5.js
Leaflet
Web Device API
DocMed Sales Data Viz


2023
A real-time data viz app that automates business insights (BI) from DocMed's e-commerce platform.
- instant access and visibility of BI
- optimized for low-compute smart TVs
TypeScript
Chart.js
GSAP
Node.js (Express)
Passport.js
SQLite (Prisma)
AWS
Lead, Software engineer
DocMed e-commerce engineers
Text-GPT-p5

2023
A genAI p5.js editor/REPL for coding beginners learning to program visually.
- immediately visualizes generated output
React (Next.js)
p5.js
OpenAI
Vercel
Docker
Verywhen

2023
A simple web utility that keeps time across timezones, useful for globe-spanning teams.
- show the current time or wind it forward or backward
Svelte
Tailwind
Luxon
localStorage