Thanks to visit codestin.com
Credit goes to github.com

Skip to content
View MyBoringFacts's full-sized avatar

Highlights

  • Pro

Block or report MyBoringFacts

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
MyBoringFacts/README.md

Hi, I’m Thadoe Hein 👋

AI Engineer focused on building production-ready machine learning systems

I design and ship applied AI systems across NLP, computer vision, and automation. My strength is not training models in isolation, but turning messy ideas into working systems under real constraints like cost, latency, and limited compute.

I use modern AI tooling to move fast, but I stay opinionated about architecture, evaluation, and failure modes.

What I Work On

  • End-to-end ML systems from data ingestion to deployment
  • Retrieval-augmented generation pipelines and document intelligence
  • Face recognition and video processing systems under constrained resources
  • ML infrastructure glue: batching, orchestration, monitoring, and automation

I care about systems that survive outside notebooks.

Selected Focus Areas

  • Applied NLP and LLM Systems
    RAG design, prompt evaluation, embedding strategies, and retrieval tradeoffs

  • Computer Vision Systems
    Face detection, tracking, embedding pipelines, and large-scale similarity search

  • Production ML Engineering
    Dockerized services, async pipelines, cloud deployment, and cost-aware design

Tooling I Actually Use

Python • PyTorch • Hugging Face • LangChain • Docker • AWS • Next.js

I do not reinvent everything from scratch. I integrate, debug, and optimize until the system works reliably.

Background

  • B.Sc. in Computer Science, Assumption University of Thailand
  • GPA: 3.7
  • Hands-on experience across NLP, generative AI, and applied ML systems

I’m early in my career, but I bias toward building things that run, fail, and improve over time.

Contact

Portfolio: https://thadoe.me
Email: [email protected]
GitHub: https://github.com/MyBoringFacts
LinkedIn: https://linkedin.com/in/thadoe

AI is not the goal. Reliable systems are.

Pinned Loading

  1. car-booking-system-project-using-PERN-stack car-booking-system-project-using-PERN-stack Public

    SCSS 1

  2. Gemini-Meeting-Analyzer Gemini-Meeting-Analyzer Public

    Google Gen AI Intensive Course Capstone 2025Q1 Google Gen AI Intensive Course Capstone 2025Q1

    Jupyter Notebook

  3. InsightDocs- InsightDocs- Public

    Video version available here: https://github.com/MyBoringFacts/video-insights-generator

    Python

  4. mt5-base-finetune-on-burmese-squad-dataset mt5-base-finetune-on-burmese-squad-dataset Public

    Fine-tuning mT5 for generative question answering in Burmese using translated SQuAD data — research project at LLU Lab, Thailand.

    Jupyter Notebook

  5. Receipt-Annotation Receipt-Annotation Public

    Receipt Processing and Annotation Pipeline

    Python

  6. ViT-CIFAR10 ViT-CIFAR10 Public

    This repo contains files , model and code . The ViT is trained on CIFAR-10 dataset and it is capable of getting 99.5% train accuracy and 93% test accuracy.

    Jupyter Notebook