Nelson Mwaura

I’m a data engineer and data scientist with 4+ years of experience designing robust data pipelines, processing structured and unstructured datasets, and deploying machine learning models. I focus on turning messy, real-world data into trustworthy analytics repositories that teams can rely on.

In my current role, I designed, built, and validated data ingestion pipelines using Python and SQL to process datasets from existing ERP systems into centralized analytics repositories. I enforce strict validation rules to maintain single-source-of-truth accuracy, and I evaluate transformations to ensure correctness and reproducibility.

I also support predictive modeling by performing extensive data processing, analysis, and feature engineering for Python-based forecasting. When needed, I navigate and modify real backend codebases (Django) to enable clean, reusable workflows for local experiments—always with documentation and maintainability in mind.

Earlier, I delivered scalable backend and data-driven systems for diverse global clients as a freelance Backend Developer & Data Specialist, with an emphasis on end-to-end ownership, reliable ingestion systems, and performance optimization. I’ve also built project work like an EHR-focused clinical data warehouse with automated data validation and error notification, and an end-to-end heart disease risk prediction model using pandas and scikit-learn.