Open to opportunities

Aaron Osei

@aaronosei

Message

I am a Senior Data Scientist and Data Engineer specializing in ML, NLP, and cloud-native analytics.

United States

Message

What I'm looking for

I’m seeking a senior role combining machine learning and cloud data engineering, with cross-functional collaboration, production-grade deployments, and opportunities to deliver executive insights and scale enterprise analytics.

I have over 12 years of experience architecting data-driven solutions across higher education, HR analytics, and finance, working extensively with Azure, Databricks, and Microsoft Fabric to turn complex problems into measurable results.

I build production-grade predictive models and real-time analytics pipelines — for example, an XGBoost retention model with SHAP that increased intervention precision by 40%, an enterprise Lakehouse using Delta Lake and Medallion architecture, and automated ETL workflows that cut processing time by 50%. I also developed a LangChain- and Azure OpenAI-powered HR document assistant and an NLP-based essay recommender to improve program matching.

I am a collaborative communicator who bridges technical and non-technical teams, delivers executive-level insights, and leads cross-functional initiatives to scale cloud-native architectures and drive organizational impact.

Experience

Work history, roles, and key accomplishments

Current

Senior Data Scientist & Data Engineer

Current

University of Oklahoma

Nov 2021 - Present (3 years 9 months)

Led design and deployment of an XGBoost retention model with SHAP, boosting student intervention precision by 40%. Architected a Lakehouse on Azure Data Lake Gen2 and Databricks and automated ETL with ADF/Databricks, reducing data processing time by 50% while delivering executive Power BI dashboards.

Azure Data Factory Databricks Delta Lake XGBoost Power BI Python NLP MLFlow

Senior HR Data Scientist

University of Oklahoma

Jul 2017 - Nov 2021 (4 years 4 months)

Built predictive analytics for talent retention and mobility forecasting, automating legacy HR reporting into modular ETL and decreasing reporting latency by 60%. Applied Oaxaca-Blinder wage gap analysis to support DEI initiatives and delivered interpretable, compliance-aligned analytics to HR stakeholders.

Python SQL Tableau ETL Predictive Analytics Oaxaca Blinder Automation)HR Analytics

HR Data & Analytics Analyst

Integris Health

Feb 2015 - Jul 2017 (2 years 5 months)

Developed automated SQL Server pipelines and Tableau dashboards to deliver real-time HR metrics to executives, improving cross-team visibility and decision-making. Integrated Oracle BI and designed dashboards to monitor turnover, diversity, and succession planning outcomes.

SQL Server Tableau ETL Dashboards Data Integration

HR Data Analyst

Sonic

Jun 2012 - Feb 2015 (2 years 8 months)

Automated Excel-based reporting with Python, reducing reporting turnaround by 75% and enabling dynamic workforce dashboards for promotions and role realignment. Conducted EDA to uncover attrition and compensation trends that informed HR decisions.

Python Excel Automation SQL Tableau