ML Data Operations · Simulation & Synthetic Data · Technical Program Execution Kigali, Rwanda
Electronics and Telecommunication Engineer working across UAV operations, machine-learning data quality, automation, and simulation-data delivery. At Zipline, I have helped turn operational and ML-partner needs into reliable workflows, clear delivery plans, quality controls, and measurable process improvements.
My work at Zipline has included:
- Simulation and synthetic data: planning scenario work, prioritizing backlogs, validating artifacts, and coordinating delivery handoffs for perception and autonomy teams.
- Perception data and annotation quality: leading image, video, and 3D point-cloud workflows; developing standards and QA practices; and supporting a 30+ person organization.
- Operations automation and reporting: improving data, quality-control, and reporting workflows, including automation that reduced manual reporting effort by 95%.
- UAV field operations: flight operations, systems maintenance, technical training, and operational process improvement.
These are descriptions of my professional experience, not public Zipline projects. My public repositories below are personal examples, templates, and learning resources; they contain no Zipline code, operational data, or internal systems.
- Data Annotation Guide — reference guide to annotation workflows, quality practices, and ML data operations. Read online
- QA Automation Pipeline Template — starter template for dataset validation and QA reporting workflows.
- Computer Vision Analysis — OpenCV example for image complexity and sparsity analysis.
- Workforce Analytics Dashboard Template — starter project for SQL-based workforce metrics and dashboard workflows.
- Webhook Metrics Reporter — small Python web-service example for receiving events and reporting metrics.
- Interactive Assessment App — lightweight browser assessment app built with vanilla JavaScript and local persistence.
- Google Apps Script Automation — example of Sheets-backed forms and workflow automation.
- Kagoma BBC Contributions App — React Native mobile-app project for basketball-club contributions and expense tracking.
- Quick Courses — modular study materials for Python, pandas, NumPy, JavaScript, SQL, annotation, and ETL validation.
- ALX and systems coursework — foundational C, shell, and systems-engineering exercises.
- ML data operations: simulation-data planning, synthetic-data delivery, dataset readiness, provenance and manifest checks, experiment comparison, annotation operations, and perception-data quality.
- Quality and execution: QA design, taxonomies and SOPs, root-cause analysis, backlog prioritization, delivery planning, stakeholder coordination, technical reporting, and team coaching.
- Analytics and automation: Python, SQL, pandas, Databricks workflows, APIs, ETL-style reporting, Google Apps Script, Google Sheets automation, and JavaScript.
- AI-assisted development: AI prompting and specification, Codex, GitHub Copilot, output review, testing, and release-readiness checks.
- Data, analytics & ML: Databricks, Python, SQL, pandas, Mode Analytics, Grafana, Weights & Biases, Prefect, and annotation tools.
- Automation & collaboration: Google Workspace, Apps Script, Jira, Slack, Confluence, Odoo, and REST APIs.
- Development environments: Linux, command line, Git, VS Code, containers, and remote/Devbox environments.
- Web & mobile: JavaScript, HTML/CSS, React Native, and Expo.
- Kinyarwanda: Native
- English: Fluent; professional working proficiency
- French: Fluent; professional working proficiency
- Swahili: Basic; elementary proficiency