Skip to content

Selected work

Projects & Creations

Things I built end to end. Web apps, machine learning tools, and a game.

  1. AutoSec

    Python · Java · C++ · LangGraph · LLM Agents · CodeQL · AWS EC2 · Static Analysis

    • Contributing to an agentic security pipeline that autonomously detects, exploits, patches, and verifies software vulnerabilities using LLMs.
    • Primary owner of end-to-end pipeline runs across 200+ Java and C++ repositories, producing the scans, exploits, and patches behind the paper's evaluation.
    • Generated per-CVE CodeQL taint queries from fix commits on AWS EC2, verifying 505 of 1,817 candidate traces across 18 CWEs as patcher input, and certified per-CVE proof-of-vulnerability exploits against NVD and GHSA. This exposed patches that left vulnerabilities exploitable.
    • Improved pipeline reliability to run unattended with LangGraph caching, exponential-backoff retries, and idempotency keys, eliminating prior startup failures.
    • Co-authoring the work as a research manuscript for USENIX Security 2027, emphasizing system reliability, verification, and auditability.
    View Project

  2. GreenLeaf Lending Analytics - RBC Business Analysis Hackathon

    React · JavaScript · SVG · CSS · Data Analysis

    • Built an interactive dashboard scoring loan readiness 0-100 from 25K+ sensor readings across 8 B.C. farms, letting RBC lenders stress-test approval scenarios live.
    • Quantified a $47K seasonal return on 4.6% of input spend, giving lenders a concrete margin-of-safety figure to underwrite against.
    • Linked same-day alert response to 4.2× more crop stress relieved, tying operational discipline to measurable loan risk.
    View Project

  3. Goblin's Keep

    Java · Maven · JUnit · Mockito

    • Led backend development of a 2D tile-based escape game by architecting game logic and AI systems, coordinating code reviews and integration across a team of developers.
    • Implemented dynamic goblin AI using a modified A* pathfinding algorithm with randomized patrol logic, enhancing difficulty balance and replayability.
    • Refactored core classes (MapGenerator, CollisionChecker, Entity) to eliminate God classes and duplicated code, improving long-term maintainability following OOP best practices.
    • Engineered a unit and integration testing suite with JUnit and Mockito, achieving 96% line coverage and 92% branch coverage to ensure correctness across all gameplay interactions.
    Play GameView Project

  4. FraudLens - SFU DSSS ML Hackathon 1st Place

    Python · Scikit-learn · Pandas · NumPy

    • Won the first ML Hackathon hosted by the SFU Data Science Student Society by building a multi-class fraud detection pipeline for fraud detection.
    • Designed a validation and cleaning pipeline enforcing consistent data types and value ranges, applying constraint-based reasoning to flag real-world transaction impossibilities.
    • Engineered three predictive features: balance mismatch flag, balance difference (after minus before), and balance error (amount minus balance difference) to expose accounting inconsistencies for the model.
    • Trained a class-weighted Random Forest over a logistic regression baseline, tuning number of trees, max depth, and minimum samples against Macro F1 to improve recall on rare minority fraud classes.
    View ProjectView LinkedIn Post