Jiasheng Huang

Highlights

• Won 1st place in the Adult Track at the SylphAI AdaL Hackathon
• Built an AI security review system on top of AdaL, delivered as three integrated layers: a pre-push git hook, a GitHub Action, and a unified web dashboard
• Engineered a pre-push hook that pipes git diffs into AdaL headless mode and blocks pushes containing SQL injection, hardcoded secrets, broken auth, or unsafe deserialization before code reaches GitHub
• Developed a React + Vite + Tailwind dashboard with FastAPI backend and GitHub OAuth that aggregates review history from three sources: PR comments, commit comments, and locally blocked pushes parsed from ~/.adal/sec-review.log
• Designed a one-line installer (curl ... | bash) that verifies prerequisites, installs the AdaL CLI, triggers first-time login, and drops the pre-push hook into any git repository
• Proposed the 'AdaL Expert Pack' framework — a reusable architecture for shipping vertical reviewers (security, performance, style) on top of a single AI agent engine with shared install and distribution patterns

Highlights

• Built a multi-agent pipeline that parses SCU Academic Progress exports to identify requirement gaps and generate personalized schedules
• Implemented a Gemini-powered planning agent that accepts natural language preferences and recommends courses based on remaining degree requirements
• Integrated RateMyProfessor API with parallel thread execution to enrich recommendations with professor ratings, difficulty scores, and would-take-again percentages
• Designed an interactive weekly calendar UI in Streamlit that maps course schedules from SCU Find Course Sections data
• Architected modular agent structure with roadmap for PDF-based requirement parsing, orchestrator agent, and email automation with human-in-the-loop approval

Highlights

• Built a customer-facing submission portal for brokers and business owners to provide KYB/KYC information and upload supporting documents
• Developed a structured underwriter console that consolidates submitted data, uploaded documents, missing information, and reviewer notes into a single case view
• Reduced manual email and attachment tracking by turning fragmented broker/business-owner submissions into organized underwriting cases
• Designed missing-information indicators and evidence-based review sections to help underwriters triage cases and make faster decisions
• Created a deploy-ready MVP with sanitized seed data and a Vercel-based demo setup for fast public walkthroughs

Highlights

• Built a personalized meal logging and macro tracking system that reduced manual diet tracking time by ~50% compared with using ad-supported free apps
• Developed reusable React components and responsive layouts for meal entry, daily macro summaries, and progress-oriented dashboards
• Designed REST-style Express API endpoints with JWT authentication, protected routes, and user-specific data access
• Modeled relational PostgreSQL tables for users, meal entries, and nutrition data, using SQL queries for persistent tracking and daily summaries
• Implemented timezone-safe date filtering with UTC storage and local-date UX to ensure accurate daily nutrition records
• Improved production reliability with request timeout handling and retry logic for Render cold-start scenarios

Highlights

• Developed face recognition pipelines using ResNet and Vision Transformer models in PyTorch
• Processed facial image datasets and implemented training workflows for supervised recognition tasks
• Benchmarked CNN and transformer architectures through comparative performance evaluation
• Applied transfer learning and deep feature extraction techniques for computer vision tasks

Highlights

• Built with Next.js App Router + TypeScript + Tailwind CSS
• Content is centralized in data files for quick edits (projects, skills, links)
• Responsive layout with accessible navigation and subtle interactions
• Designed for fast deploys on Vercel with no backend