Zippy Vaati

Delivered a 2-week machine learning and generative AI training for 30 NGO staff, building Jupyter-based Python ML workflows. Trained participants on supervised/unsupervised learning (including XGBoost and clustering) and supported deployment of a Streamlit-based ML application using real-world agricultural datasets.

Contributed to Apache open-source projects including Apache Airflow and Apache Spark by submitting pull requests and improving documentation. Helped develop Python and data engineering solutions in collaboration with global community contributors.

Contributed remotely to data engineering projects using Python, SQL, and AWS, including designing an ETL pipeline for job-seeker and job-opening data to support improved data-driven matching. Mentored young data engineers by sharing best practices for ETL workflows and SQL queries via Datakind’s Slack channel.

Engaged with the Women in Data UK community by participating in webinars, workshops, and mentorship programs to strengthen technical and leadership skills. Collaborated with professionals across data engineering, analytics, and AI.

Built the Revenue Assurance and Billing functions from scratch, setting SOPs and integrating CRM and finance systems for improved data consistency and visibility. Automated reconciliation and gap analysis to cut manual work by 40% and reduced errors, while dashboards improved executive decision-making by 30%.

Designed and maintained Pentaho ETL pipelines consolidating revenue data across five Sub-Saharan countries to support reconciliation, forecasting, and KPI tracking. Developed automated dashboards that improved executive decision-making by 30% and performed mobile money partner reconciliations to prevent leakage and detect anomalies.

Built and maintained ETL pipelines processing 10M+ customer records from CRM, billing, ERP, network, and digital platforms. Developed Power BI and Tableau dashboards and implemented Python ML pipelines for churn prediction and customer segmentation, improving operational analytics reliability through automated validation and data governance.

Collaborated on marine insurance solutions for Kenya’s leading insurers, automating cargo tracking and policy generation. Implemented Python backend services and APIs for real-time cargo status and data integration, adding automation scripts and validation checks in an Agile/Scrum environment.

MSc in Business Computing (Data Science). Completed all coursework and is preparing for thesis defense.

Bachelor’s degree in Business Information Technology (BBIT), specializing in software development and networking. Built skills in system development, database management, and IT infrastructure to support business goals.

Grade: A-(79/84 points)

Completed secondary education and sat KCSE examinations. Achieved a mean grade of A-(79/84 points).