Skip to content

Zanwen Fu / Engineer & FounderMake something
people want

Agents are easy to demo and hard to depend on. I build the ones people depend on.

I founded , a personal financial analyst, and built every part of it myself. More than 5,000 investors have signed up. Every number in it is computed, not generated. When Wall Street disagrees, it stands by its own and shows you both.

Before that I was an early employee at , the code-repair agent acquired by Sonar (opens in new tab). I’ve also shipped agentic AI at Robinhood and reliability infrastructure for Binance’s Web3 Wallet.

What I took from all of it: the model is rarely what decides whether an agent holds up. Everything around it is. That’s my work now: , the fastest and most reliable AI alert for anything on the web. I’m also building Agent OS, an operating system for AI agents.

01Work

Selected work

All projects & research

Products

Research

All projects & research Architecture, experiments, and source code

02Experience

Experience

Robinhood

· Agentic AI Team

May 2026 – Aug 2026

Machine Learning Engineer Intern · Menlo Park, CA

Worked on Robinhood Cortex, the AI assistant for Robinhood Gold, with a focus on adoption and engagement. Solo-designed and shipped a proactive agent that decides when something deserves a customer’s attention instead of waiting to be asked. Cut false positives five-fold in backtesting with no material event missed, scaled coverage 30× at flat latency, and caught and fixed a production delivery failure that monitoring had missed.

Python · Go · Kafka · Kubernetes · Airflow · DynamoDB

Jul 2025 – Dec 2025

Founder & Sole Engineer · Durham, NC

Founded VYNN to give every investor a personal financial analyst, and built every part of it: the research agents, the valuation engine, the backend, the app and the infrastructure it runs on. More than 5,000 investors have signed up. It turns six to twelve hours of an analyst’s research into a sourced report and a live Excel model in about two minutes, for about three cents. Code computes every number, and every release is checked against a set of reference valuations before it ships.

Python · LangGraph · FastAPI · React · TypeScript · MongoDB · Redis · Docker · Hetzner

Research Engineer · Singapore

Advised by Prof. Abhik Roychoudhury at NUS. Worked on lifting the agent to 51.6% on SWE-bench Verified, building Self-Fix and targeted replay into the repair backend. Built the JetBrains IDE plugin end to end: a three-way merge on the syntax tree, SonarLint analysis sent straight to the agent, and live streaming with per-step feedback. Sonar acquired AutoCodeRover in February 2025; the same team’s Foundation Agent later reached the top of the unfiltered SWE-bench leaderboard at 79.2%.

Kotlin · Python · IntelliJ Platform SDK · GumTree · SonarLint · JGit · OkHttp

Binance

· Web3 Wallet Team

Jul 2025 – Oct 2025

Software Engineer Intern · Singapore

Built API automation and performance infrastructure for the Web3 Wallet team. Integrated regression checks into CI/CD, engineered concurrent workloads to exercise backend services under load, and instrumented monitoring to surface data-consistency failures before release.

Java · JMeter · Postman

Aug 2025 – Apr 2026

Graduate Teaching Assistant · Durham, NC

Teaching assistant to Prof. Robert Duvall. Co-designed and ran CS 590 (Software Development Studio), where graduate students build AI debugging agents inspired by AutoCodeRover and deploy full-stack applications. Mentored teams in CS 408 and CS 390 on software architecture, DevOps, and LLM-oriented programming, shipping production software for outside clients.

Python · Docker · GitLab CI/CD · WebAssembly

Jan 2024 – Jul 2025

AI Researcher · Singapore

First author of LUMINA, a four-agent system that screens medical literature for systematic reviews; designed and built it and ran the evaluation. Across 15 published reviews it missed 8 of 378 included studies (98.2% mean sensitivity, 87.9% specificity), a 35× lower miss rate than a reimplementation of Li et al. (2024), at under a cent per citation. The pipeline has screened about 150,000 candidate abstracts in all.

Python · scikit-learn

Earlier

ST Engineering · Full-Stack Software Engineer

May 2023 – Aug 2023

Built a full-stack railway dashboard connecting backend services to live train-status reporting across Singapore’s MRT network.

Centre for Quantum Technologies (Singapore) · Quantum Software Engineer

May 2024 – Dec 2024

Built a quantum experiment compiler and controller for FPGA/DDS hardware, with threaded execution and live data visualization.

NUS Computing · Research Assistant

Feb 2024 – Nov 2024

Built LLM tools and human data-collection pipelines for research at NUS Computing.

03About

Research, industry & ownership

I care a lot about creating real value for people, solving a real problem and building something that’s actually useful. Beyond solving the problem, I also want the people using it to have a great experience. I founded and built alone, and more than 5,000 people signed up. Along the way I learned that the agent pipeline underneath and the way a missing number shows up on screen are the same problem.

Now I’m doing my master’s at Duke, advised by Prof. Bhuwan Dhingra (opens in new tab). My research tests coding agents, and the AI that judges their work, against real developers. Simulator Review, a study of AI reviewers, is under way. I built , which messages you the moment something you care about happens, in Slack, Discord, Telegram or email. In a public live race against seven other alerts, it was first on the most stories and caught the most. I’m also building Agent OS, an operating system for AI agents that keeps everything they do on record and delivers only what has been verified. And on my own, I’m studying whether poisoned news can change what an AI financial agent tells its user, and whether a fine-tuned model forecasts football results or only remembers them.

Before Duke, I studied at NUS and worked on with my advisor, Prof. Abhik Roychoudhury (opens in new tab). Sonar later acquired it. Since then I’ve worked on backend reliability at Binance, and at Robinhood I shipped a proactive agent that cut false positives five-fold in backtesting.

I’ve also been a teaching assistant for Prof. Robert Duvall (opens in new tab) at Duke, in three software engineering courses where students ship working systems.

Duke University

M.S. Computer Science · AI/ML · Advisor: Prof. Bhuwan Dhingra (opens in new tab)
Scholar profile (opens in new tab)

2025–2027

National University of Singapore

B.Comp. Computer Science · Honours, Distinction · Advisor: Prof. Abhik Roychoudhury (opens in new tab)
Distinction in Software Engineering (opens in new tab) · HKU exchange

2021–2025

Open to full-time engineering roles from May 2027.

05Teaching

Teaching software engineering

Graduate TA at Duke CS for Prof. Robert Duvall (opens in new tab). Across three courses I've run the hands-on infrastructure side: 48 students across 15 teams shipping systems with Docker, CI/CD, and AI agents, on labs and benchmarks I build and maintain.

Graduate course covering production software engineering, Docker, CI/CD, API design, and server deployment — culminating in students building an AI debugging agent (inspired by AutoCodeRover) and a full-stack social media application.

Mentoring teams on architecture, testing, DevOps, and full-stack development to deliver production-ready software for outside clients.

Leading weekly labs covering AI agents, LLM-oriented programming, Docker, APIs, and system design.

Teaching materials — labs, benchmarks, and the LLM-teammate pipeline