About
I like building end-to-end: from the model that makes the decision, to the API serving it, to the server it runs on. A system isn't finished when the code compiles — it's finished when it's deployed, monitored, and quietly doing its job.
My background sits at the intersection of geospatial, WebGIS and computer vision — photogrammetry, point clouds and LiDAR, object detection and segmentation on aerial, satellite and industrial imagery, the map front-ends (OpenLayers/MapLibre) and the backend system design to run them — with modern LLM, RAG and MLOps work layered on top.
I started this blog to teach younger software engineers the things I wish someone had told me at the beginning of my career — the practical notes on LLMs, RAG, computer vision and shipping AI that I had to learn the hard way.
Tech Stack
Programming Languages
Frameworks & Web
AI / ML & Computer Vision
Databases
Servers, DevOps & Deployment
Specialized Domains
Areas of Expertise
Geospatial & Computer Vision
- •3D point cloud classification & segmentation at scale
- •Object detection for infrastructure and photogrammetry pipelines
- •WebGIS front-ends (OpenLayers, MapLibre) over PostGIS pipelines
LLM Integrations, RAG & AI Agents
- •RAG document Q&A with vector search and source grounding
- •Agentic workflows with tool use and function calling
- •LLM orchestration across OpenAI, Anthropic, and open-source models
- •Production ML infrastructure — containerized, monitored, retrainable
Scalable Web Architectures
- •Full-stack React + FastAPI / Flask platforms
- •Auth, payments, email, analytics — end-to-end delivery
- •5+ platforms currently running in production
Servers, DevOps & Deployment
- •Linux server setup from bare VPS — Docker Compose, Nginx, SSL, backups
- •CI/CD pipelines and automated deploys via GitHub Actions
- •Celery workers, cron jobs, Gunicorn — background processing and scheduling
- •Monitoring and alerting with Prometheus, Grafana, cAdvisor, node-exporter
- •Operating a fleet of production servers on Hetzner, AWS, and GCP
Teaching: AI Engineering from Scratch
Build AI applications from scratch in Python — one free, hands-on episode at a time.
Open-Source Projects
Production-shaped code you can clone, read, and run — the same patterns I write about.
Working together
I take on freelance work in exactly the areas above — computer vision and point clouds, geospatial and WebGIS, LLM/RAG pipelines, and the system design to run them in production. Discovery sprints, consulting, or a project delivered end to end.
Let's Connect
I enjoy talking shop with other engineers and researchers — LLM integration patterns, 3D perception pipelines, or just swapping notes on shipping things to production. Always open to a technical exchange.