Engineer & founder building production-grade autonomous agents, grounded in strong software engineering to solve real-world problems.
I build agentic AI systems that actually work in the real world — reliable, observable, and designed to survive production, not just demos.
I'm a Software Engineer and MS Computer Science (AI/ML) student at Duke University, focused on building production-grade autonomous systems — from multi-agent orchestration and LLM tooling to the distributed backends that run them reliably at scale.
I'm the sole founder and engineer of VYNN AI, an agentic financial analyst platform built end-to-end and deployed to ~500 pilot users.
Previously, I designed core components of AutoCodeRover, an autonomous code repair system acquired by Sonar, integrating agentic reasoning directly into JetBrains IDEs. In parallel, I've led research as sole first author on multi-agent LLM frameworks for medical text mining, achieving 98.2% sensitivity across 15 systematic reviews (~150K citations).
This summer, I’ll be joining Robinhood in Menlo Park as a Machine Learning Engineer on the Agentic AI team, continuing my focus on building autonomous systems that operate reliably at real-world scale.
Systems that are reliable, observable, and production-ready — not just demo-ready. I care deeply about turning ideas into robust software that solves real problems and serves real users.
Agent harness design — the infrastructure layer that makes agents actually work in production. The agent itself is the easy part; the harness that makes it reliable, observable, and debuggable is what I want to build.
M.S. Computer Science (AI/ML)
2025 – 2027 · Graduate Teaching Assistant
Duke Scholar
View official scholar profile
B.Comp. in Computer Science (Honours)
2021 – 2025 · Distinction
Distinction in Software Engineering
View verified credentialExchange Semester at HKU (Fall 2023)
Building agent infrastructure and tooling — prototyping reasoning loops, composing toolchains, and supporting evaluation pipelines for Robinhood's next-generation AI financial products. Bringing production experience from building multi-agent systems at VYNN AI and AutoCodeRover.
Designed, built, and deployed a full-stack agentic financial analysis platform single-handedly — from LangGraph multi-agent backend and FastAPI orchestration layer to React dashboard and production infrastructure on Hetzner Cloud. Serves ~500 pilot users with institutional-quality equity research (DCF modeling, news intelligence, automated reports) in under 7 minutes end-to-end.
Architected and led CS 590 (Software Development Studio), where graduate students build AI debugging agents inspired by AutoCodeRover and deploy full-stack applications. Also mentored teams in CS 408 and CS 390 on software architecture, DevOps, and LLM-oriented programming — shipping production software for real clients.
Built the JetBrains IDE plugin end-to-end for autonomous code repair — GumTree-based 3-way AST merge, embedded SonarLint analysis, and real-time SSE streaming with per-step developer feedback. Enhanced the agentic repair backend with LLM-as-a-Judge self-improvement, lifting SWE-bench Verified to 51.6% (state-of-the-art among open-source agents). Core technology acquired by Sonar.
Built backend validation infrastructure for Binance's Boosters campaign — automated API regression suites in CI, load-tested services to ~500K concurrent transactions via JMeter, and instrumented monitoring to catch consistency failures before production. Worked directly with backend and Web3 Wallet engineers to root-cause and patch defects, cutting resolution time by 40%.
Led research as first author on a multi-agent AI framework for medical evidence synthesis. Designed and built LUMINA, a four-agent LLM framework that automates citation screening for medical systematic reviews — achieving 98.2% sensitivity and 87.9% specificity across 15 SRMAs (~150K citations) with a 35× reduction in false negatives vs. prior state-of-the-art.
Automates institutional-quality equity research that traditionally takes analysts 6–12 hours into a single autonomous pipeline under 7 minutes. A LangGraph supervisor orchestrates five specialized agents — financial data collection, DCF modeling, news intelligence, report generation, and a 3-layer recommendation engine with deterministic validation — serving ~500 pilot users in production. Built end-to-end as sole engineer: 50,000+ lines of Python, React/TypeScript frontend with real-time WebSocket streaming, and Docker-based infrastructure on Hetzner Cloud.
System Architecture
< 7 min
Full equity analysis — data scraping, DCF modeling, news intel, and PDF report generation
72%
Latency reduction via parallel agent execution and result caching
Real-Time
Dual WebSocket streams for live prices and news with auto-reconnect and health checks
~500
Pilot users on production Hetzner Cloud infrastructure with zero-downtime deployments
SSE streaming with log batching, multi-conversation management, downloadable XLSX + PDF reports
Live prices, stock charts, news aggregation
Multi-portfolio, real-time P&L, holdings CRUD
6 interactive chart types (area, bar, pie, radar, scatter, treemap), one-click PNG export
Company, sector, and global market reports with batch generation and smart polling
OAuth, passwordless login, HTTP-only cookies, cross-tab sync, user-scoped storage
Brought autonomous code repair from research to a production developer tool. AutoCodeRover is a multi-agent system that resolves real GitHub issues end-to-end — reproducing bugs, searching codebases across 7 languages via tree-sitter, generating patches with iterative refinement, and self-correcting through an LLM-as-a-Judge reviewer. I built the JetBrains IDE plugin end-to-end in Kotlin: a conversational agent UI with real-time SSE streaming, GumTree-based three-way AST merge for conflict-free patch application, embedded SonarLint static analysis, and a feedback loop where developers can critique any reasoning step to trigger guided re-runs. On the backend, I designed the self-fix agent that diagnoses inapplicable patches and autonomously replays the pipeline from the most suspicious stage — lifting SWE-bench Verified to 51.6%. The core technology was acquired by Sonar. Sonar Foundation Agent, built on the AutoCodeRover core, has since reached 79.2% on SWE-bench Verified — #1 on the leaderboard (Feb 2026).
Repair Pipeline Architecture
51.6%
SWE-bench Verified (Jan 2025)
State-of-the-art across 2,294 real GitHub issues — highest among open-source agents
13.2%
Resolve Rate Improvement
Lifted SWE-bench Verified from 38.4% (Jun 2024) to 51.6% (Jan 2025) — via Self-Fix Agent with LLM-as-a-Judge and interactive feedback loops
3-Way
AST Merge (GumTree)
Conflict-free patch application when local code has diverged from agent's baseline
7
Languages Supported
Tree-sitter search across Python, Java, JS, TS, C/C++, Go, PHP
Describe a bug → ACR localizes, patches, and validates autonomously
Embedded static analysis for Java/Python with one-click ACR fixes
GumTree conflict resolution across baseline/modified/patched
Critique any agent reasoning step — triggers guided pipeline re-run
LLM-as-a-Judge diagnoses inapplicable patches and replays from failure point
Auto-captures IDE build and test failures with one-click ACR submission
Designed and built LUMINA, a four-agent framework that automates citation screening for medical systematic reviews and meta-analyses. A classifier agent triages citations, a detailed screening agent applies PICOS-guided Chain-of-Thought evaluation, a reviewer agent audits each decision via LLM-as-a-Judge, and an improvement agent self-corrects when disagreements arise — mirroring the human peer-review process. Evaluated on 15 SRMAs across ~150K citations from BMJ, JAMA, and Lancet journals: achieved 98.2% mean sensitivity (10 of 15 at perfect 100%) with 87.9% mean specificity. Outperforms published sensitivity baselines by Li et al. (37%) and Strachan (58%) by 35× fewer missed studies.
98.2%
Sensitivity
10 of 15 reviews at perfect 100%. vs. 37% (Li et al.) and 58% (Strachan) — 35× fewer missed studies
87.9%
Specificity
reduces manual screening by ~10× — reviewers examine only ~12% of citations instead of 100%
15
Systematic Reviews
~150K citations from BMJ, JAMA, Lancet — <$0.01 per article
Teaching software engineering, DevOps, and agentic AI systems to undergraduate and graduate students at Duke.