My Profile Photo

Chen Hongshan

Studying at NUS as a year 2 undergraduate Computer Science student.

About Me

Welcome to my page. I am a Year 2 student at the National University of Singapore (NUS), majoring in Computer Science. I mainly work with Java and have built a solid foundation in OOP and algorithms through coursework and projects. Outside class, I enjoy exploring interactive media and game/graphics development (OpenGL). Lately, I’ve also been diving into AI and LLMs — most recently building a RAG-based NetEase Cloud Music AI agent backend demo, and experimenting with a multimodal hybrid model at TikTok TechJam 2025.



Education

National University of Singapore

Bachelor of Computing in Computer Science

Awards: NUS Science and Technology Undergraduate Scholarship (2024-2028)

Expected Graduation Date: June 2028

Academic Courses:

  • MA1522 Linear Algebra
  • ST2334 Probability and Statistics
  • CS1231S Discrete Mathematics
  • CS2030S Programming Methodology II (Object-Oriented Programming in Java)
  • CS2040S Data Structures and Algorithms
  • CS2100 Computer Organisation
  • CS3241 Computer Graphics


Skills

Programming Languages

  • Proficient: Java
  • Working knowledge: Python, JavaScript, HTML/CSS
  • Basic: C, C++

Backend Development

  • Proficient: Spring Boot; RESTful API design and implementation
  • Working knowledge: Maven (dependency management, build & packaging); Swagger/OpenAPI (API documentation & testing); OkHttp (HTTP client integration)

Data & Storage

  • Working knowledge: MySQL (basic schema & CRUD); H2 (local dev/demo); Redis (cache integration & basic operations)

Engineering & Environment Management

  • Working knowledge: Spring Profiles (dev/prod separation); Docker & docker-compose (one-command dependencies with volumes and healthchecks)
  • Familiar: reproducible setup and graceful degradation concepts (configuration layering, environment variables, README-aligned setup)

RAG & LLM Integration

  • Working knowledge: RAG pipeline integration; OpenAI-compatible APIs (e.g., DashScope); prompt engineering and output control (ChatGPT, Qwen)
  • Basic: FAISS (vector indexing and similarity retrieval)

Machine Learning & Multimodal

  • Working knowledge: BERT/FastBERT for text classification/filtering; CLIP for multimodal representation/validation
  • Basic: PyTorch; Transformers (inference and experimentation workflow)
  • Familiar: vLLM (inference serving exploration)

Graphics & Interactive Media

  • Working knowledge: OpenGL (coursework/project experience)

Documentation & Tools

  • Proficient: Git, GitHub, Markdown
  • Working knowledge: Mermaid; JetBrains IDEs; Microsoft Office (Word/PowerPoint/Excel); Aseprite


Experiences

NetEase Cloud Music Intelligent Customer Support Agent (Minimal RAG)

Description: A minimal RAG-based customer support agent backend that integrates retrieval, guarded prompting, and reproducible local deployment.

Highlights:

  • Implemented RESTful endpoints with Swagger/OpenAPI for rapid testing and demo recording.
  • Built a dev/prod configuration split using Spring Profiles (dev with H2; prod with MySQL + Redis).
  • Added a Redis cache with TTL and graceful fallback, keeping the main request path available even when Redis is down.
  • Containerized dependencies via docker-compose (MySQL + Redis with volumes and healthchecks) for one-command local setup.
  • Maintained an architecture-first README (Mermaid diagrams and startup steps) aligned with the implementation.

Project Link: NetEase-music-agent-backend-demo

Duration: Dec 2025 - Jan 2026

Tech Stack: Java | Spring Boot | Spring Data JPA | Maven | H2 | MySQL | Redis | Docker Compose | Swagger/OpenAPI | OkHttp | OpenAI-compatible LLM API


Harmonia — Hierarchical Multimodal Hybrid Review Validation with RAG

Description: A hierarchical review filtering system using AI models we trained, routing requests across fast and accurate stages to separate genuine feedback from spam at scale.

Highlights:

  • Designed a multi-stage pipeline: rule-based preprocessing → fast classifier routing → multimodal validation → RAG-backed final verification.
  • Trained and evaluated text classification models (e.g., FastBERT/BERT-family) and integrated confidence-based routing to balance latency and accuracy.
  • Incorporated multimodal signals (e.g., CLIP) to handle cases where text-only signals are insufficient.
  • Supported both single-review and batch processing workflows for practical experimentation and benchmarking.

Project Link: Harmonia

Duration: Aug 2025 - Sep 2025

Tech Stack: Python | PyTorch | Transformers | FastBERT/BERT-family | CLIP | FAISS | Qwen | RAG | vLLM (inference) | OpenAI APIs


OpenGL Graphics Coursework

Description: A collection of OpenGL-based coursework demos exploring core real-time rendering concepts and interactive controls.

Highlights:

  • Implemented graphics pipeline fundamentals, including transformations, camera controls, and scene organization.
  • Built shader-based rendering effects (e.g., lighting, materials, and texturing) as part of course assignments.
  • Added interactive input handling for navigation and parameter tuning during demos.

Project Link: OpenGL Coursework

Duration: Aug 2025 - Dec 2025

Tech Stack: C++ | OpenGL | GLUT



Extra Curricular Activities

NUS Piano Ensemble

Role: Member

Duration: Aug 2024 – Present

  • Actively participate in club activities.
  • Performed 4 piano duets with a partner in the annual concert.
  • Completed 3 performances in performance classes and received guidance from the professor on piano technique.

NUS Climbing Club

Role: Member

Duration: Aug 2025 – Present

  • Holds the Singapore SNCS Level 2 certification.
  • Maintains weekly high-intensity training sessions with the club.

Chengdu Shude High School International Division Orchestra & Choir

Role: Principal Pianist

Duration: Jan 2022 – Jan 2024

  • Served as the piano accompanist for the school orchestra and choir, and hosted and performed in 6 concerts.
  • Performed 5 piano solo pieces.