class AIEngineer:
def __init__(self):
self.name = "Chris Kechagias"
self.role = "AI Engineer"
self.location = "Thessaloniki, Greece"
self.education = "B.Eng. Automation & Control Engineering (2012)"
self.background = "15 years retail operations → AI engineering"
self.expertise = [
"LLM Application Development",
"FastAPI Backend Systems",
"Production Deployment & Testing",
"Prompt Engineering & Modular Design"
]
self.current_projects = {
"retail_api": "97% test coverage • PostgreSQL • Supabase",
"chatbot_api": "Dual GPT-5.4 models • Streaming • YAML prompts",
"telegram_bot": "Webhook integration • Real-time routing"
}
def build_production_systems(self):
return "Deployed APIs • Real-world solutions • Test-driven development"
def get_philosophy(self):
return "Build, deploy, iterate. Production over perfection."Current Stack
 |
 |
|||||
 |
 |
 |
 |
 |
 |
Learning & Upcoming
 |
 |
 |
 |
 |
 |
Production-ready FastAPI application for fashion retail inventory management
Tech Stack: FastAPI • PostgreSQL • SQLModel • Alembic • pytest • Docker
Highlights: 97% test coverage • UUID architecture • Auto-generated SKUs • Deployed on Render + Supabase
Advanced chatbot with modular prompt engineering and dual GPT-5.4 model architecture
Tech Stack: FastAPI • OpenAI API • PostgreSQL • Docker • YAML
Highlights: Dual models (5.4-mini + 5-nano) • Modular prompts (8 presets) • Streaming responses • Context window management
Microservice connecting chatbot API to messaging interface
Tech Stack: Telegram Bot API • Ngrok • FastAPI
Highlights: Webhook-based • Real-time routing • Production deployment
RAG Systems • Multi-Agent Architectures • Workflow Automation
Building production LLM applications with FastAPI, PostgreSQL, and modern deployment practices