I'm a Computer Engineering student at Umm Al-Qura University focused on Agentic AI and Multi-Agent Systems, ranked in the top 5% of 12,000+ participants in the KAUST AI Program and trained inside IBM's AI Lab.
My work spans the full lifecycle of applied AI from designing multi-agent pipelines and LLM orchestration layers to shipping full-stack platforms with Laravel and computer vision applications with PyTorch. At IBM's AI Lab I designed a healthcare platform powered by four specialized AI agents and built the LLM orchestration layer that unites them into a single pipeline.
I care about building things that work end-to-end: offline LLM pipelines, RAG systems, and production-style AI workflows, not just proof-of-concept notebooks.
Open to: AI/ML Engineer Roles · Agentic AI & Multi-Agent Systems Roles · Software Engineering Internships
| Domain | Proficiency | Details |
|---|---|---|
| Agentic AI & Multi-Agent Systems | Advanced | Multi-agent orchestration, LLM pipeline design |
| Large Language Models | Advanced | Prompt engineering, RAG pipelines, local/offline inference |
| Computer Vision | Intermediate | PyTorch-based vision applications |
| Deep Learning | Intermediate | Neural networks, model training and evaluation |
| Web Scraping & Automation | Advanced | BeautifulSoup, Selenium, OCR pipelines |
| Full-Stack Engineering | Advanced | Laravel MVC, PHP, relational databases |
Aafiyah — Multi-Agent Healthcare Platform
Built at the IBM AI Lab: turns unstructured doctor notes into structured care plans and medication schedules through four specialized AI agents working as one coordinated system.
| Attribute | Detail |
|---|---|
| Stack | Node.js · Express · Gemini API · JWT |
| Agents | 4 specialized AI agents |
| Security | Role-based access control |
| Repository | github.com/AdemCE-eng/Aafiyah |
What it does: Designed the LLM orchestration layer connecting clinical-note summarization, treatment-plan tracking, medication reminders, and patient Q&A agents into a single production-style pipeline. Presented to IBM evaluators and industry mentors.
Wathiq — AI Legal Document Review Platform
AI-powered legal document review platform that analyzes and improves contracts using OCR and a fully local LLM.
| Attribute | Detail |
|---|---|
| Stack | Python · OCR · Ollama (local LLM) |
| Languages | Arabic and English support |
| Repository | github.com/qo43/thka-q9a |
What it does: Extracts text from PDFs and images via OCR, identifies weak or missing legal clauses, and generates drafting suggestions using a local AI model — no external API cost, no data leaving the machine.
Content Inspiration — Local LLM Research Automation
Research automation tool that scrapes, downloads, and summarizes articles through a 4-stage local LLM pipeline — fully offline inference at zero API cost.
| Attribute | Detail |
|---|---|
| Stack | Python · Requests · Beautiful Soup · Ollama · Streamlit |
| Pipeline | 4-stage: scrape → download → summarize → present |
| Cost | Zero API cost — fully offline |
| Repository | github.com/AdemCE-eng/Content_Inspiration |
What it does: Scrapes articles from the Google AI Blog with rate-limiting and retries, generates concise summaries with a local Mistral model via Ollama, and presents everything in an interactive Streamlit dashboard with filtering, search, and read tracking.
Trend Web — Full-Stack Social Platform
Complete Twitter-style platform with tweets, replies, retweets, likes, and follows, engineered end-to-end on Laravel MVC.
| Attribute | Detail |
|---|---|
| Stack | Laravel · PHP · MySQL · Tailwind CSS |
| Architecture | MVC, built with Laravel |
| Features | Follow network · media gallery · avatar upload |
| Repository | github.com/AdemCE-eng/Trend_Web |
What it does: Full social platform proving full-stack range beyond AI work — authentication, profile management, and a complete content-interaction system built from scratch.
Apr 2026 – Jun 2026 · 3 mos · Remote
Completed IBM's 10-week AI Industry Immersion program, mentored by IBM experts. Designed a healthcare platform with 4 specialized AI agents for clinical-note summarization, treatment-plan tracking, medication reminders, and patient Q&A, and designed the LLM orchestration layer connecting them into a unified production pipeline.
Scope of work:
- Applied Agentic AI, Multi-Agent Systems, RAG, Agile, and Design Thinking in a collaborative team environment
- Designed and built the LLM orchestration layer unifying four AI agents
- Presented the final solution to IBM evaluators and industry mentors
Agentic AI Multi-Agent Systems RAG LLM Orchestration Agile Design Thinking
| Recognition | Details |
|---|---|
| KAUST AI Program | Top 5% of 12,000+ participants |
| IBM AI Lab | AI Developer Trainee — 10-week Industry Immersion |
| UQU Computer Club | Recognition for contributions — Project Management Committee |
Learning:
- Agentic AI system design at production scale
- Advanced RAG architectures
- Computer vision with PyTorch
Building:
- Multi-agent AI platforms (Aafiyah)
- Local-first LLM tooling (Content Inspiration, Wathiq)
- Full-stack applications with Laravel
Exploring:
- Multi-Agent Systems & LLM orchestration
- Offline / local-inference AI pipelines
- Applied computer vision
Open To:
- AI / ML Engineer roles
- Agentic AI & Multi-Agent Systems opportunities
- Software Engineering internships
Building at the intersection of agentic AI, multi-agent systems, and full-stack engineering.