Data Engineering
Kenya Soil Health Data Warehouse
An end-to-end BI pipeline on Kenyan agronomic trial data — data warehousing, OLAP querying, interactive visualisation, and data mining
PythonSQLiteStreamlit
View details → Hi, I'm
George Mark
I develop data systems that help organisations make informed decisions and achieve goals — currently studying Computer Science at the
University of Nairobi.
I enjoy solving problems, hoping to change the world one line of code at a time.
Skills
Languages
PythonJavaScriptSQLHTML & CSS
Frameworks
DjangoFlaskFastAPINode.jsAstro
Tools & APIs
Git & GitHubLinuxPostgreSQL
Experience
Data Engineering Intern · Data XL
Jul 2026 — Present
Building data and ML infrastructure at a Nairobi data-engineering firm that delivers complex data systems across Africa.
- Developed a machine learning pipeline that scores 200,000+ leads daily — a logistic-regression model with continual learning, so scores stay accurate as new outcome data arrives without manual retraining
- Decoupled the client onboarding application from heavy text-extraction work by deploying a cloud message queue — extraction requests now process asynchronously instead of blocking the app while new members are registered
- Built a FastAPI service exposing chat, vision, and voice capabilities against Scaleway's generative AI models, giving internal products a single API for AI features
PythonFastAPIMachine LearningMessage QueuesScaleway
Hackathon Team Member · H4CKIT NewGen
Jun 2025 — Jun 2025
Built the Health Service Locator — an offline-accessible health facility finder for Kenyan citizens.
- Built a USSD backend using Node.js to manage stateful user sessions, allowing offline users to navigate multi-level menus to locate healthcare services
- Engineered a geolocation routing algorithm that queried the Google Maps API to return the top 5 nearest health facilities within a 10km radius — by Mozart Moguche
Node.jsUSSDSMS APIs
Education
Bachelor of Science in Computer Science · University of Nairobi
Sep 2023 — 2027 (expected)
Coursework spanning math, business, networks, software development, and artificial intelligence.
- Relevant courses: Software Engineering, Machine Learning Algorithms & Programming, Artificial Intelligence Applications, Computer Network Security, Embedded Systems & Mobile Programming
- Built an end-to-end business intelligence pipeline on Kenyan soil-health trial data for the Business Intelligence & Analytics course — a galaxy-schema data warehouse with OLAP querying, an interactive Streamlit dashboard, and data-mining workflows — view on GitHub
- Member, Rotaract Club of University of Nairobi — contributing to The Rotary Fund in support of community development and humanitarian work, and networking with local community leaders through regular club sessions and team-building exercises