I build AI systems designed to run in production — not just in notebooks.
My background is E-commerce Technology, which means I approach AI engineering from both sides: I understand the business domain and the technical stack that makes it work at scale.
Most AI projects stop at the demo. Mine don't. When I build, I think about: Cost, Security, Observability, Improvement loops
A multi-agent LLM system that handles end-to-end sales conversations for e-commerce.
class MyApproach:
niche = "LLM Agents + GenAI × E-commerce domain"
principles = [
"Real data over toy datasets",
"Measure before claiming it works",
"Cost is a feature, not an afterthought",
"Security is not the last step",
]
currently_learning = [
"Advanced agent evaluation frameworks",
"LLM fine-tuning for domain adaptation",
"Multi-modal inputs for product understanding",
]AI / LLM 
Machine Learning 
Infrastructure 
- UUIDv7: Why You Should Stop Using Auto-increment Integers and UUIDv4
- Analyzing Agentic Workflow Architecture via OOP: A loop.py Case Study
→ All posts on thaig2pro.github.io
I'm open to AI Engineer Intern / Fresher / Junior roles — especially teams building real AI products in e-commerce.
