I'm passionate about building intelligent systems that solve real-world problems. My work sits at the intersection of machine learning, backend engineering, and AI applications — from predictive models and computer vision systems to APIs, automation, and scalable data workflows.
shadrack = {
"current_role": "AI & ML Engineering Intern @ Vunoh Global",
"currently_building": "Production ML pipelines, backend systems & AI workflows",
"learning": ["MLOps", "Distributed Systems", "Advanced ML"],
"core_focus": ["Machine Learning", "Computer Vision", "Backend Systems", "LLM Applications"],
"stack": ["FastAPI", "Django", "Docker", "PostgreSQL", "PyTorch", "XGBoost"],
"superpower": "Turning messy real-world data into clean, usable AI systems",
"fun_fact": "I care as much about backend structure as model accuracy"
}|
ML system for real estate pricing in Nairobi. Scraped 460+ listings across 34 neighborhoods Tech: Python · XGBoost · Scikit-learn · BeautifulSoup · Streamlit · Dash |
Automated clinical prediction pipeline. Predicts Normal/Abnormal outcomes Tech: FastAPI · PostgreSQL · SQLAlchemy · XGBoost |
|
LLM-powered workflow engine. Natural language → structured workflows Tech: Django · OpenAI API · SQLite · JSON Processing |
Data engineering + ML system for car import decisions in Kenya. Scraping vehicle data from Japan marketplaces (SBT, BE FORWARD, CarFromJapan, JCT, AAA Japan) Tech: Python · PostgreSQL · Pandas · Scikit-learn · FastAPI · Streamlit/Dash |
Sprint 1: MLOps (Docker & MLflow) — 🟦🟦🟦🟦🟦🟦⬜⬜⬜⬜ 60%
Sprint 2: AI Engineering Best Practices — 🟦🟦🟦🟦⬜⬜⬜⬜⬜⬜ 40%
Sprint 3: Advanced SQL Optimization at Scale — 🟦🟦🟦⬜⬜⬜⬜⬜⬜⬜ 30%
Sprint 4: Open Source Contributions — ⬜⬜⬜⬜⬜⬜⬜⬜⬜⬜ 0%
Continuously shipping code. Watch this space
"Torture the data, and it will confess to anything."