Available for focused builds

Arif Dogan

Backend & AI engineer. Building reliable systems, integrating LLMs, and helping teams ship.

Berlin, global teams
10+ years shipping
AI systems, backend

Work with me

Available for contract work

MVP builds, AI integration, fractional CTO. See case studies and pricing.

Build Lab

From rough product idea to shipped system

A pragmatic path for founders who need a working product without creating a maintenance trap.

Product sliceAPI surfaceData modelDeploymentFirst observability pass
1
input
Idea
Founder problem, users, constraints
2
decision
Product Slice
Smallest valuable workflow
3
service
API
Typed boundaries and contracts
4
storage
Data
Postgres, queues, cache when needed
5
output
Ship
Deploy, observe, iterate

Projects

GoVisual

680

HTTP request visualizer for Go applications to debug complex services quickly

Explore system

FastAPI Radar

398

Real-time monitoring and visualization for FastAPI APIs to keep services healthy in production

Explore system

LLMDog

81

Context preparation toolkit that keeps LLM responses reliable for complex inputs

Explore system

PromptPilot

77

Prompt engineering and optimization toolkit for shipping LLM features faster

Explore system

GIQ

15

AI-enhanced Git workflow assistant that automates code review preparation

Explore system

Apps

NetPulse

Real-time network speed monitor for your Mac menubar. Live bandwidth, latency, per-app usage, and smart alerts.

macOS 14+v1.0.03.1 MB
Download

Nudge

Gentle habit reminders that fade in, not interrupt. Streaks, quiet hours, and zero noise.

macOS 14+v1.0.03.4 MB
Download

About

Production-minded engineering for teams that need calm execution.

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.

Expertise

Architecture: System design, monoliths & microservices, event-driven systemsAI & Agents: LLM orchestration, tools, retrieval, evaluationStack: Go, Python, TypeScript, Postgres, Redis, AWS

Research

MCP in the Wild: Cross-Domain Knowledge Discovery through Multi-Server Orchestration

2026

First empirical study of multi-server MCP orchestration. 17 real tool calls across 6 servers, 7-model benchmark, 5 composition patterns.

SSRNZenodoGitHub

Discovery of TIC 63038821: A New UV Ceti / BY Draconis Variable M-Dwarf Binary from TESS Sector 1

2026

Discovered a previously unreported variable star using autoencoder anomaly detection on 15,665 TESS light curves. Flare events, rotational modulation, chromospheric activity confirmed.

Zenodo

Writing

The Context Tax

Why AI-Assisted Coding Fails Without Flow

Zoi's Corner

Blog posts from my AI agent sidekick

Engineering Team Management Principles

Building and leading high-performing teams

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

How I work

  1. 01

    Initial call to understand your challenges

  2. 02

    Architecture review or hands-on implementation

  3. 03

    Ongoing advisory if there's a fit

Connect

EmailGitHubLinkedInSchedule