FL Alzheimer's Classification
Evaluating federated learning for Alzheimer's Disease classification using 3D MRI data from ADNI with differential privacy.
FlowerMONAI3D CNN+3
Read moreTurning coffee into code
Hey there! 👋
I'm Tin Hoang
const role = "AI Research Engineer & MLOps"
London, UK — originally from Vietnam 🇻🇳
After 7 years building AI systems in production, I moved to London to pursue my MSc and dive deeper into research. Currently exploring how AI can help with medical diagnosis while keeping patient data private.
🇻🇳 Vietnamese, now based in London☕ Powered by coffee🎮 Will debate you about RTS games📚 Believe learning never stops🤖 Teaching machines to see since 2017
Something I built
Ask my AI anything about me
I built a chatbot that knows my entire professional history. It uses RAG (Retrieval-Augmented Generation) with a small language model to answer questions about my experience, projects, and research. Give it a try!
Tin's AI Assistant
Powered by RAG + SLM
Online
What's Tin's experience with deep learning?
🤖
Tin has over 6 years of experience in deep learning, specializing in computer vision and OCR. He developed LODENet, a novel architecture for text recognition that was published at ICPR 2020. Currently, he's researching federated learning for medical AI applications at the University of Surrey.
Try asking:
Built with Kotaemon • Retrieval-Augmented Generation • Hosted on HuggingFace
My Story
From tinkering with computers in Vietnam to researching AI in London — here's how I got here.
Growing up
Where it all began
📍 Vietnam
Born and raised in Vietnam, where I first discovered my love for technology and problem-solving. Spent countless hours tinkering with computers and dreaming about what they could do.
2014
Engineering foundations
📍 HCMC University of Technology
Started my journey in Computer Engineering. This is where I fell in love with the elegance of algorithms and the power of code to solve real problems.
2017
First steps into AI
📍 Cinnamon AI
Joined Cinnamon as an intern, and everything changed. Suddenly, I wasn't just writing code — I was teaching machines to see and understand.
“The moment I saw my first model actually work, I was hooked.”
2020
Published researcher
📍 ICPR 2020
Published my first paper on LODENet, a novel OCR architecture for Chinese and Japanese text. Seeing my work in an international conference felt surreal.
“From "I have no idea what I'm doing" to published author.”
2021
Patent holder
Filed my first patent for OCR technology. Never thought I'd be an inventor, but here we are.
2023
AWS Solutions Architect Pro
Passed one of the hardest cloud certifications on my first attempt. Turns out those late nights studying actually paid off.
“Pro tip: don't take a 3-hour exam on an empty stomach.”
2024
New chapter
📍 University of Surrey, UK
Moved to London to pursue my MSc in Artificial Intelligence. After 7 years in industry, I wanted to dive deeper into research.
“Leaving everything familiar behind to chase a dream.”
Now
Building what's next
📍 London, UK
Researching federated learning for privacy-preserving medical AI. Also building tools, writing, and figuring out what comes after this.
“The journey continues...”
What I'm Into Right Now
A glimpse into what's keeping me busy these days.
Building
This AI chatbot →
A RAG system that knows everything about me
Federated Learning research
Privacy-preserving AI for Alzheimer's classification
Learning
GenAI
Building with AI
Cooking
Cooking Vietnamese food
Reading
AI Engineering - by Chip Huyen
Learning about AI engineering best practices
System Design - by Alex Xu
Learning about system design best practices
AI/ML papers
Always learning
Playing
Age of Empires IV
Strategy games keep my mind sharp
StarCraft
APM training for life
Fun fact: I've been playing Age of Empires since I was a kid. It taught me more about resource management than any business book. 🏰
Things I've Built
A selection of projects from my research and engineering work. From academic papers to production systems.
Face Diffusion Generation
Benchmark study on diffusion models for human face generation with InfoNCE loss and SegFormer-based segmentation.
PyTorchStable DiffusionLoRA+5
Read more
SLM Profile RAG
Profile-aware RAG chatbot that prioritizes a main document, retrieves vectorized resume/profile data, and serves responses locally via Ollama + Streamlit.
StreamlitLangChainChromaDB+6
Read more
Solar Forecasting
Deep learning framework for forecasting Global Horizontal Irradiance in Ho Chi Minh City using satellite-derived data.
PyTorchTransformerMamba+5
Read moreLatest from the Blog
Thoughts on AI, MLOps, and lessons learned from building production systems.
technicalFeatured
From Chaos to Clarity: Standardizing MLOps and Lessons Learned
How we centralized AI research, reduced onboarding time by 92%, and cut cloud costs by $6,000/month—plus hard-won lessons from 6+ years in production AI.
15 October 202412 min read
MLOpsProduction ML+4
Read article