Martin Kilombe, Data Engineer & Analyst. I build the pipelines that move 10M+ records a month, and the analyses that turn them into decisions worth trusting.
Data Engineer & Analyst with 4+ years across finance, consumer behavior and operations. Currently Data Engineer & Lead Data Analyst at Cloud Intelligence: dashboards that lifted decision effectiveness by 40%, a real-time data-quality framework watching 100+ metrics, and local-LLM automated reporting.
Before that I built the plumbing itself: Python/SQL ETL moving 10M+ records a month at 99.5% uptime on PostgreSQL and Google Cloud. An actuarial-science foundation means the statistics underneath are as sound as the pipelines.
Presented as plates: each is a real, shipped project, and every finding is measured from the data itself.
Production-grade stock data pipeline merging Polygon.io and Yahoo Finance: market-aware scheduling, JSONB metadata, batch inserts, full monitoring.
Performance study of Apple, Microsoft, Netflix, Google, Amazon and Meta: moving-average crossovers, volatility, correlation structure.
Interactive dashboards on Netflix content trends and UK job demographics: time-series, KPI tiles, comparative views.
A Random Forest model shipped as a Dockerized Django app with PostgreSQL: instant, explainable loan assessment from income and credit history.
ETL for 10M+ records/month (−60% manual prep) · PostgreSQL & Cloud SQL warehouses for 5 business units · 99.5% pipeline uptime with Docker orchestration.
Dashboards that lifted decision effectiveness 40% · real-time data-quality framework across 100+ metrics · SQL runtimes cut 30% · local-LLM automated reporting.
Python/SQL automation halved reporting turnaround · built data-quality monitoring pipelines that cut errors 20% · KPI definition and dashboards across teams.
Market research and competitive analysis · data models, cubes and metadata for actuarial ad-hoc analysis.
Thank you — it's in my inbox. I'll get back to you soon.
Email me directly at martin@martinkilombe.dev.