Open to opportunities

Mohammed Madi

@mohammedmadi

Message

I build production LLM agent systems, machine learning pipelines, and full-stack applications.

Jordan

Message

What I'm looking for

I'm looking to build production AI and ML systems, especially LLM agents, RAG applications, and scalable full-stack products where I can apply data science and cybersecurity experience.

I've built production AI systems at CybWok, including a LangGraph-based multi-agent clinical triage platform combining deterministic rules, LLM patient interviews, voice triage, RAG retrieval, and FHIR-compliant records. I also developed provenance tooling with DAG reasoning traces and deterministic replay, plus a prompt-evolution engine that reduced token usage by 74.5% while maintaining 96.7% accuracy.

At Jawaker, I integrated Mintroute voucher redemption for more than 10 million registered users and rewrote the Android payment flow. At EastNets Holding, I created synthetic banking data for anti-money-laundering training, built a graph neural network for money-laundering detection, and delivered an explainable ML dashboard.

I've also shipped full-stack features with .NET, Vue.js, TypeScript, and PostgreSQL at Miaplaza. My projects span game-theoretic LLM reasoning, PDF malware detection, cybersecurity challenges, and plant-disease classification.

I'm ranked third globally in Huawei ICT Innovation 2024, and I enjoy sharing what I learn through cryptography, competitive programming, Python automation, and neural-network workshops.

Experience

Work history, roles, and key accomplishments

Current

CTF Challenge Writer

Current

MetaCTF

Mar 2024 - Present (2 years 5 months)

Designed AI/ML exploitation challenges (Graph Node Injection, adversarial image perturbations) and cryptography challenges (ECC, RSA, lattice-based schemes) used in national and international competitions.

Cybersecurity Cryptography AI ML CTF

AI/ML Engineer

CybWok

Nov 2025 - Apr 2026 (5 months)

Architected a LangGraph-based multi-agent triage system implementing the Briggs 7-tier acuity protocol, combining a deterministic rule engine with LLM-driven patient interviews. Integrated real-time voice triage using OpenAI Realtime API, Whisper STT, and YAMNet audio event detection, and built a full provenance layer with DAG reasoning traces and SHA-256 ProofPackets.

LangGraph OpenAI API Whisper YAMNet RAG ChromaDB FastHtml SQLModel PostgreSQL Docker Python

Backend Software Development Engineer Intern

Jawaker

Jul 2025 - Oct 2025 (3 months)

Integrated a voucher redemption system with Mintroute into the Ruby on Rails backend, enabling a new monetization channel for 10M+ registered users. Rewrote the entire in-app Android payment flow, improving reliability and reducing payment-related bug reports.

Ruby on Rails Ruby Android Payment Systems

Data Scientist Intern

EastNets Holding

Jul 2024 - Sep 2024 (2 months)

Generated realistic synthetic bank transaction datasets using statistical distributions derived from production data for anti-money-laundering model training. Built a Graph Neural Network (GNN) model for money laundering detection and developed a Streamlit dashboard with end-to-end ML pipeline visualization including SHAP explainability.

Python Streamlit SHAP Machine Learning Data Generation

Full Stack Developer Intern

Miaplaza Inc.

Jun 2023 - Nov 2023 (5 months)

Implemented client-side caching strategies that reduced page load times by 37% across the platform. Refactored legacy modules, improving readability and achieving an additional 5% performance gain, and shipped features across the full stack using .NET, Vue.js, TypeScript, and PostgreSQL.

.NET Vue.Js TypeScript PostgreSQL Caching Performance Optimization