Jiasheng Huang

Software Engineer / AI & ML Builder · Santa Clara, CA

Jiasheng Huang

Building AI Agents, Robot Perception, and Full-Stack Systems

Computer Science and Engineering student at Santa Clara University and Software Engineering Intern at Vigiles Robotics, working on semantic mapping for an LLM-driven inspection robot. I build AI agents, vision-language pipelines, and full-stack apps.

View Projects Resume GitHub LinkedIn

At a glance

School
Santa Clara University
Major
Computer Science and Engineering · Expected Jun 2027
Currently
Software Engineering Intern @ Vigiles Robotics
Focus
AI agents · Vision-language models · Full-stack
Open to
Software Engineering / AI / ML Internships

Experience

Where I’ve worked

Software Engineering Intern

Vigiles Robotics Inc.

Semantic Mapping for an LLM-Driven Inspection Robot

Jul 2026

Milpitas, CA

  • Worked on an offline semantic mapping pipeline that turns robot LiDAR/RGB-D captures into a map labeled with rooms and objects (SLAM → room segmentation → object detection → map export)
  • Implemented a watershed-based room-segmentation module in Python (distance transform, flood fill, doorway detection) to replace an unavailable proprietary dependency, with unit tests
  • Integrated vision-language-model object detection to identify objects in camera frames and attach their 3D locations to the map
PythonSLAMLiDAR / RGB-DVision-Language ModelsROS 2

Featured

Projects

SecReviewer — AdaL Track 1st Place Winner

AI-powered security guard for every git push. Built on SylphAI's AdaL coding agent, shipped as three layers: a local pre-push git hook that blocks bad code, a GitHub Action for PR-time review, and a unified review dashboard that aggregates findings across all sources. Stops SQL injection, hardcoded secrets, and broken auth before code leaves the laptop. Won 1st place in the AdaL Track at the SylphAI AdaL Hackathon.

AdaLGitHub ActionsReactViteFastAPISQLiteOAuthBash

Highlights

  • Won 1st place in the AdaL Track at the SylphAI AdaL Hackathon
  • Built an AI-powered security review system on SylphAI's AdaL coding agent, shipped as three layers: a local pre-push git hook, a GitHub Action, and a unified review 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
GitHubDemo

Course Planning Agent

AI-powered course planning system for SCU students. Upload your Academic Progress export and get personalized next-quarter schedule recommendations with professor ratings — no more switching between Workday, RateMyProfessor, and your transcript. Backend deployed on Render, frontend on Vercel.

PythonFastAPIReactTypeScriptSQLiteGemini APIGoogle OAuthMulti-Agent

Highlights

  • Built a multi-agent course planning system that parses SCU Academic Progress exports to identify degree-requirement gaps and generate personalized next-quarter schedules
  • Implemented a Gemini-powered planning agent that converts natural-language preferences into course recommendations
  • Enriched recommendations with RateMyProfessor ratings via parallel thread execution
  • Built REST API endpoints in FastAPI for transcript upload, plan generation, and per-user memory, backed by SQLite with Google OAuth sign-in
  • Built a React + TypeScript frontend; deployed the backend on Render and the frontend on Vercel
GitHubDemo

Underwriting Copilot

End-to-end underwriting copilot MVP that streamlines KYB/KYC submission and underwriter review. The system includes a customer-facing submission portal for brokers and business owners, plus a structured underwriter console that organizes submitted business information, documents, missing fields, risk signals, and decision evidence into a single review workflow.

Next.jsTypeScriptTailwind CSSVercelPythonFastAPI

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
GitHub

Fitness Tracker (Full-Stack Web App)

Built a full-stack nutrition and meal tracking web app to replace ad-heavy free fitness apps and streamline my personal daily diet tracking workflow. The app provides a responsive React UI, JWT-authenticated REST API, PostgreSQL persistence, daily macro tracking, date-based filtering, and end-to-end deployment on Vercel, Render, and Neon.

ReactReact RouterViteNode.jsExpressPostgreSQLJWTSQLGitVercelRenderNeon

Highlights

  • Built and deployed a full-stack nutrition tracking app (Vercel/Render/Neon), cutting personal meal-logging time by ~50% with JWT auth, REST APIs, and relational schemas
  • 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
GitHubLive

Face Recognition with ResNet and Vision Transformer

Developed a face recognition system using CNN and transformer architectures to study deep visual representation learning.

PythonPyTorchResNetVision TransformerComputer Vision

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
GitHub

Personal Portfolio Website

Modern, recruiter-friendly portfolio built with a clean single-page layout, reusable content data, and strong project cards.

Next.jsTypeScriptTailwind CSSVercel

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
GitHub
Interested? Let’s connect →

About

A bit about me

I’m a Computer Science and Engineering senior at Santa Clara University (expected June 2027). I enjoy building AI agents, vision-language pipelines, and full-stack software that’s reliable, scalable, and easy to use.

This summer I interned at Vigiles Robotics, working on a semantic mapping pipeline that turns robot LiDAR/RGB-D captures into maps labeled with rooms and objects for an LLM-driven inspection robot.

Relevant coursework: Advanced Data Structures, Theory of Algorithms, Operating Systems, Software Engineering, Machine Learning and Data Mining, Artificial Intelligence, and Web Search and Information Retrieval.

I’m currently looking for Software Engineering / AI / ML opportunities where I can contribute to production-grade systems and keep learning fast.

Skills

Technical toolkit

Languages

PythonC/C++JavaSQL (PostgreSQL)JavaScriptTypeScriptHTML/CSS

Machine Learning

Multimodal Sensor FusionVision-Language ModelsLLM Agent InterfacesRAGLangChainPyTorchTensorFlowNumPyPandasScikit-learn

Frameworks & Tools

ROS 2ReactNode.jsExpressDjangoFastAPIRESTful APIsGitLinux/UnixCI/CDClaude CodeCursor

Databases & Cloud

PostgreSQLSQLiteAWS (S3, Bedrock)VercelRender

Resume

Download my resume

Want the one-page version? Download the PDF resume for the full details.

Download Resume

Contact

Let’s connect

Fastest way to reach me is email. You can also find me on GitHub and LinkedIn.

jhuang13@scu.eduGitHubLinkedIn