Available for focused builds

Arif Doganfounder & engineer. backend systems and AI, shipped.

10+ years in backend systems. Currently focused on LLM orchestration, agent architectures, and production AI. I work with early-stage teams as a fractional CTO or hands-on engineer—architecture, implementation, and technical leadership. Based in Berlin, working with teams globally.

★ Open source

5 small tools.
1.3k stars on GitHub.

1.3kgithub · 2024 — present

Work

GoVisualHTTP request visualizer for Go applications to debug complex services quickly681
FastAPI RadarReal-time monitoring and visualization for FastAPI APIs to keep services healthy in production398
LLMDogContext preparation toolkit that keeps LLM responses reliable for complex inputs81
PromptPilotPrompt engineering and optimization toolkit for shipping LLM features faster77
GIQAI-enhanced Git workflow assistant that automates code review preparation15

Research, 2026

MCP in the Wild: Cross-Domain Knowledge Discovery through Multi-Server OrchestrationFirst empirical study of multi-server MCP orchestration. 17 real tool calls across 6 servers, 7-model benchmark, 5 composition patterns.2026
Discovery of TIC 63038821: A New UV Ceti / BY Draconis Variable M-Dwarf Binary from TESS Sector 1Discovered a previously unreported variable star using autoencoder anomaly detection on 15,665 TESS light curves. Flare events, rotational modulation, chromospheric activity confirmed.2026

Writing

The Context TaxWhy AI-Assisted Coding Fails Without Flowweb
Engineering Team Management PrinciplesBuilding and leading high-performing teamspdf

These articles reflect how I think about teams, systems, and long-term maintainability—the same lens I use when advising clients.