SYSTEM_ONLINE
|
STACK: Laravel · React · MySql · LLM · Python
|
STATUS: Available
|
--:--:--
SYSTEM_MANIFEST
Available_For_Deep_Technology_Fusion
LLM_ALERT
LLAMA_3_PERSONALITY_SYNC_COMPLETE
CORE_PROCESS.EXE
ASK_ME_ANYTHING_TERMINAL_READY
chenghong_terminal.sh
// click anywhere to open terminal
ASK_ME_ANYTHING_READY
CONTEXT: projects · stack · experience
Powered by Claude API
chenghong@portfolio ~ bash

~/portfolio $ whoami

Full-Stack
Developer
who ships.

Role
Full-Stack Dev
Stack
Laravel · React
Focus
AI · LLM Tooling
Status
● Available
01

Who
I am.

Full-stack engineer with a background in Biochemistry and 5+ years building production systems, specializing in LLM orchestration and compliance-grade workflows — seeking to apply domain knowledge in medical AI, drug discovery platforms, or healthcare management systems.

Currently deep into AI tooling: local LLM fine-tuning pipelines, browser extensions, and the intersection where backend systems meet language models.

2026-04status: building · open to opportunities
2026-03continuing LLM training pipeline · MLX + Llama 3
2026-02published chrome extension · 4 platforms
2026-01debug timezone logic · production fix

Tech
Stack.

Laravel / PHP
Primary
React
Primary
MySQL
Primary
LLM / MLX
Growing
Node / JS
Fluent
Python
Fluent
02

Selected
Projects.

01

AI-assistant QPR (Quarterly Progress Report) System Upgrade

Designed an AI Orchestration Layer managing the full LLM workflow — data preparation, prompt construction, model routing (local vs API), output parsing, and validation guardrails ,versioning and with human-in-the-loop — projecting ~33% reduction in clinician documentation time per reporting cycle.

LLMAI OrchestrationPost-processingVersioningHuman-in-the-Loop
Architectured
2026
02

Local LLM Training Pipeline

End-to-end pipeline: export conversation data from multiple AI platforms, score, filter, clean, desensitize, convert, and fine-tune. Architecture insight: scoring before desensitization prevents placeholder leakage. Working adapter: local_claude_final2.

PythonMLXLlama 3 8BClaude APIFine-tuning
Working on
2026
03

AI Chat Workbench Extension

Browser extension injecting branch-marking UI into Claude, Gemini, ChatGPT, and Grok simultaneously, enabling precise branch marking, collapsing, and navigation across hundreds of messages. Platform-specific adapters handle DOM differences across four distinct interfaces.

Chrome ExtensionJavaScriptMulti-platformDOM
Published
2026
04

Multi-model Scoring Pipeline

Two-stage classification: Claude API (Haiku) for topic judgment, GPT for format summarization. Each model used where it outperforms the other. Designed to run before data desensitization to prevent placeholder contamination in training sets.

Claude APIGPTPipeline DesignPython
Active
2026
03
01 // scope

Scope first.

Break tasks by complexity before touching code. Know the blast radius before you dig.

02 // iterate

Iterate tight.

File by file. Line by line. Fresh context when things go in circles. No spaghetti.

03 // ship

Ship, then refine.

Production first, polish second. Things that run matter more than things that look good in dev.

04

Let's build
something.

mengchh01@gmail.com ⌥ GitHub → LinkedIn
chenghong_terminal.sh — ASK me anything READY
~/portfolio $ ↵ send
ch_terminal.sh▲ restore
SYSTEM_ALERT.EXE

CHENGHONG_MENG_UNSTOPPABLE_FOUNDATION

LLAMA_3_PERSONALITY_SYNC_COMPLETE

TARGET_LOCKED: NEXT_OPPORTUNITY

You found it. Now hire me.