// Data Engineer & AI Systems

Building data systems
that matter.

10+ years designing humanitarian data pipelines for IOM, WHO, and WFP. Now applying that domain depth to AI engineering — local LLMs, geospatial analysis, and production ETL systems.

Python MS SQL ArcGIS Pro PyTorch C++ LangChain
pipeline.py — zsh
python pipeline.py --source hdx --region ukraine
INFO Connecting to HDX API...
INFO Dataset: "UKR_displacement_2025"
INFO Records fetched: 142,847
INFO Running geospatial join...
INFO Loading to SSMS → dbo.displacement
OK Pipeline complete in 4.2s

_
01 / projects

Flagship Work

001
Humanitarian Data Pipeline — Ukraine

End-to-end ETL system pulling live displacement and food security data from the HDX API into MS SQL Server, with automated ArcGIS Pro map generation and an interactive Streamlit dashboard.

Python MS SQL ArcGIS Pro HDX API Streamlit
002
Local LLM — Field Intelligence System

RAG pipeline over classified humanitarian PDF reports using Llama 3 + LangChain. Runs fully air-gapped — no data leaves the machine. Designed for privacy-sensitive field operations.

PyTorch LangChain Ollama FastAPI ChromaDB
Planned — Phase 3
003
C++ Matrix Library

High-performance custom matrix operations in C++ — SIMD optimization, cache-aware blocking, and Python bindings via pybind11. Benchmarked against NumPy.

C++ SIMD pybind11 CMake Benchmarking
Planned — Phase 4
02 / stack

Tech Stack

AI / ML
PyTorch LangChain Ollama ChromaDB Hugging Face
Data Engineering
Python · Pandas MS SQL Server SQLAlchemy HDX API ETL pipelines
GIS & Visualization
ArcGIS Pro arcpy GeoPandas Streamlit Power BI
Systems
C++ · CMake SIMD / CUDA FastAPI Docker Linux · Bash
03 / about

Background

I'm a data and AI engineer with a decade of field experience inside United Nations organizations — building the systems that track displacement, health clusters, and humanitarian response at national scale.

That background gives me something most engineers don't have: I understand why the data matters, not just how to move it. Now I'm applying the same rigor to AI engineering — local LLM deployment, geospatial pipelines, and high-performance systems.

I'm a lifelong learner and a genuine fan of algorithms and linear algebra — I see the math as the foundation that makes AI systems actually reliable, not just impressive in demos.

10+
years field experience
3
UN organizations
5W
matrix systems built
algorithms studied
Worked with: IOM WHO WFP Ukraine / Kyiv Dnipro