Full Stack AI/LLM & Backend Developer
Hi, I'm Hassan. I am a
I ship RAG systems, agentic AI and locally-hosted LLM pipelines — wired into Django/FastAPI backends and React/Next.js frontends that don't need the cloud to think and don't fall over under load.
SELECTED WORK
Magic happens behind the doors
Four rooms, one for each kind of system I build. Pick a door.
INDEX
Every project, one line each
STACK
The pipeline, end to end
I started as a Python/Django developer automating ETL pipelines and payment integrations, then moved deep into applied AI: RAG, agentic workflows, LoRA/DoRA fine-tuning and local inference with Ollama and vLLM. Today I build the whole product — API design, React/Next.js UI and Dockerized deployment — using Claude Code and AI-assisted workflows to move fast.
MY STORY
Let's go back in time.
EDUCATION & CERTIFICATIONS
Foundations
Education
AVAILABLE · NEW CONVERSATIONS
Got a project? Let's build it together.
Open to Full Stack AI/LLM Engineer, Generative AI and Backend + AI roles. Tell me what you're building and I'll get back within a day.