Product Engineer for AI Companies

Turning AI Research into
Shipping Products.

I don't just write code. I engineer full-stack applications, turning complex problems into deployed products. The bridge between your research team and your users.

Discuss Your Product

Featured Work

Product Engineering Data Visualization

The ARC Prize Foundation

Worked with the team and Mike Knoop to engineer visualization and data interfaces for the ARC-AGI benchmark.

The challenge was not just "displaying data," but defining how researchers interact with a new form of intelligence testing. I owned the end-to-end implementation of the visualization layer.

Product Impact:

  • • Visual Task Explorer: Engineered a complex SVG/Canvas based explorer allowing users to navigate hundreds of abstract reasoning puzzles.
  • • Evaluation Infrastructure: Built the "stadium" for model performance, creating high-density comparison matrices that organize results across dozens of models and the full evaluation dataset.
  • • Metadata Architecture: Designed the schema and frontend logic to organize disparate task metadata into a coherent browsing experience.

Client

ARC Prize Foundation

Founders

François Chollet & Mike Knoop

Outcome

Interactive Benchmark UI

Product Engineering Browser Extension Zotero Plugin

Zotero NotebookLM

Built for Julia Turc (Founder, Storia.ai) — a bidirectional sync engine connecting Zotero with Google NotebookLM.

Researchers using Zotero had no way to leverage NotebookLM's AI features on their libraries. Since no public API exists for consumer NotebookLM, I reverse-engineered Google's internal Boq/WIZ RPC protocol — mapping undocumented batchexecute endpoints, session token extraction, and the Scotty resumable upload flow for binary files. I then engineered a full bridge system — a Zotero plugin, a Chrome extension, and a local IPC server — to enable seamless two-way sync between the two platforms.

Product Impact:

  • • Polling Bridge Architecture: Designed a reverse-RPC system where a Zotero-side HTTP server dispatches tasks to a Chrome content script running inside the authenticated NotebookLM session.
  • • Dual-Mode Strategy: Implemented both Consumer (Free/Pro) and Enterprise API strategies, auto-detecting the user's environment and routing tasks accordingly.
  • • Bidirectional Sync: Forward sync uploads PDFs, URLs, and metadata to NotebookLM; reverse sync imports AI-generated source guides and notes back into Zotero.

Client

Storia AI

Founder

Julia Turc

Outcome

Open-Source Plugin & Chrome Extension

End-to-End Engineering

01

Full-Stack Product Development

I take ownership of the entire vertical. From database schema design to the final UI polish. I translate high-level needs into functional MVPs and scale them into production-ready applications.

02

AI Interaction & UX

Product intuition for AI. I design the "middle layer" that makes models usable—handling streaming responses, latency states, and prompt engineering within the application logic.

03

Complex Data Visualization

Translating model outputs into human insight. Whether it's embeddings, task visualizers, or performance metrics, I build the tools researchers need to understand their data.

04

Internal Tools & Evaluation

Building the infrastructure for your research. I create custom annotation interfaces, leaderboards, and evaluation harnesses that allow your team to iterate faster.

Let's build together

I partner with AI labs and startups to clear the backlog and ship critical software. If you need an engineer who cares about the product as much as the code, let's talk.