• Architected and deployed a scalable automated data ETL pipeline using Presto and Apache Hive to track QA test case automation across multiple teams and orchestrated with Airflow, integrating structured QA metadata and unstructured log data(JSON, raw text) using pattern-matching and ETL frameworks, cutting manual tracking time by ~80%.

• Engineered an end-to-end ETL data pipeline using Kafka, Pyspark and Presto, integrating 5 disparate vendor systems (Jira, TestRail, custom APIs), processing 2M+ test records daily, enabling analytics that eliminated underperforming vendors and saved $2M annually.

• Developed and launched a DAU/WAU metrics dashboard for product teams surfacing engagement insights from about 100,000 users, which boosted tool engagement and drove a 50%+ increase in active users.

• Authored a comprehensive wiki that reduced ramp-up time by 14% for junior data engineers.

• Led and mentored 3+ junior data engineers, code-reviews, improved team delivery velocity, fostered skill development, and team productivity.

• Designed, implemented, and deployed the first version of the Collaborator Dashboard that helps collaborators view their projects' metrics, increasing their productivity by 75%.

• Tech Skills: PHP, Airtable, Postgres.

• Managing the project increasing clean energy access in Africa.

• Omdena UNDP Earthquake Project - Developed a safe route algorithm for UNDP to help families reach their kids in schools, the aftermath of an earthquake using NetwrokX graph algorithm, Unity 3D and OpenStreetMap(OSMNX).

• Banking the Unbanked - Engineered a credit scoring system using non-traditional data using DBSCAN clustering(Density-Based Spatial Clustering of Applications), to help those that do not have bank accounts in Indonesia to be able to get loans.

• Omdena pandemic - Analyzed COVID-19 economic policies data using pandas, numpy, matplotlib and seaborn to find the impact on the wages loss of individuals during the pandemic

• WRI Climate change - Using NLP Topic Modeling(Word2Vec, CorEx models) programmed a tool, to understand nature based solutions that can help societies and ecosystems adapt to drastic changes in the climate and mitigate the adverse impacts of such changes for WRI(World Resources Institute).

• WRI Kenya: Constructed, using NLP Spacy NER(Named Entity Recognition) and streamlit, a tool to understand the network of corporations and persons involved in land transfer and ownership in Africa the results used to fight corruption and to promote good governance of land resources by those seeking to restore them.

The project I worked on Artificial Intelligence for Predicting The Safest Path After an Earthquake.

• Worked on OSMNX network Analysis to find district to district adjacency.

• Used dijkstra's algorithm to find the shortest path between two locations for fastest and safe travel.

• Blog: https://omdena.com/blog/artificial-intelligence-earthquake