Hello, I’m

FETHI
OMUR

Forward Deployed

Forward Deployed AI Engineer, AI Architect, AI Designer

About Me

AI Engineer building multi-agent systems and LLM-powered products with the Claude Agent SDK and MCP, grounded in deep learning. Always up for AI research collaborations.

WHAT
I DO

ENGINEER

Description

I build multi-agent systems and LLM-powered products: Claude Agent SDK and MCP orchestration, retrieval pipelines, fine-tuning and evaluation, shipped on Cloud Run and Azure.

Skills & tools
  • Claude Agent SDK
  • MCP
  • Python
  • PyTorch
  • TensorFlow
  • LLM Fine-tuning
  • Gemini API
  • RAG
  • Azure AI
  • Docker

DEPLOY

Description

I ship what I engineer — an iOS app on a live 3D globe, a Flutter app live on the App Store, and web products that stay up.

Skills & tools
  • Swift
  • SwiftUI
  • Flutter
  • Next.js
  • TypeScript
  • Supabase
  • PostgreSQL
  • Cloud Run
Skip the story

How I work

4,000+ hours in Claude Code. I run software like a tech lead whose team is AI agents: written contracts, isolated worktrees, adversarial review, and nothing called done without evidence.

Always evolving · September 2026

I rebuild this workflow as the tools change.

New models and agent tools arrive every few weeks. I test them as they land, keep what makes the work better, and change how I work — staying current is part of the job. What never changes: a written plan, independent review, and proof before anything ships.

Workflow changelog

  1. One orchestrator session plans; executor sessions build in isolated worktrees.
  2. Model tier chosen per task difficulty.
  3. Whole-task briefs with a finish line; one reviewer; test only what changed.
  4. One strong model family for every agent; a second lab's model reviews read-only.
  1. I write the plan.

    A brief becomes a plan, split into packages that never touch the same file.

    The main session is an orchestrator. It plans at full effort, and every package names the files it owns and the files it must leave alone.

  2. Plan before code.

    A critic attacks the plan before anything runs.

    A planner drafts, a critic attacks the draft, and the revised plan fans out to executors. Architecture calls get a read-only second opinion from another model family.

  3. Agents in parallel, never on the same file.

    Each agent builds in its own git worktree, under a written contract.

    Every brief says what done means, when to stop and ask, and which command proves it. Executors cannot spawn agents, add dependencies, commit or push.

  4. A second model reviews everything.

    A second model re-runs every command before anything merges.

    Findings come with a file, a line, why it is wrong and how to show it fails. The second model only reads; at most two fix rounds, then the orchestrator decides.

  5. Nothing ships without proof.

    Agent reports are claims; the checks run again before every merge.

    The acceptance commands are run again before any merge, and each non-obvious decision becomes a dated ledger row with its reason and its undo.

My 3D avatar, on a round podium, conducts eight orange Claude Code blocks and three white Codex knots with a baton; each wakes on its cue.
Me, conductingI conduct the agents.I set the tempo, and every agent comes in on its cue.
A terminal window holding the twelve tools one task used, from the prompt to the merge: Claude Code, Claude Agent SDK, MCP, git, TypeScript, React, Next.js, three.js, Codex, Vitest, Playwright and Vercel.
One task, from the prompt to the merge: every tool it used, in the order it acted.

Under the hood.

My tech stack, in groups. In bold: the tools this one task used.

Builds AI agents with

  • Claude Code
  • Codex
  • Claude Agent SDK
  • MCP
  • LangGraph
  • LangChain

Models & APIs

  • Claude API
  • OpenAI API
  • Gemini API
  • Hugging Face Transformers
  • vLLM

Trains & fine-tunes

  • PyTorch
  • TensorFlow
  • LoRA · QLoRA · PEFT
  • RLHF · DPO
  • scikit-learn

RAG & data

  • pgvector
  • Pinecone
  • FAISS
  • PostgreSQL
  • Supabase
  • SQLite
  • Firecrawl

Evaluates & observes

  • Langfuse
  • Ragas
  • DeepEval
  • pytest · CI
  • Vitest
  • Playwright

Writes code in

  • Python
  • TypeScript
  • Swift
  • Dart
  • C#
  • C++
  • SQL

Ships apps with

  • SwiftUI · iOS
  • Flutter
  • React
  • Next.js
  • three.js
  • FastAPI
  • Unity

Deploys with

  • git
  • Vercel
  • Docker
  • Kubernetes
  • Google Cloud
  • AWS
  • Azure AI Studio
  • n8n

Used in this task: Claude Code, Claude Agent SDK, MCP, git, TypeScript, React, Next.js, three.js, Codex, Vitest, Playwright, Vercel

Speaks: Turkish (native), English (C1), Azerbaijani (C1), Italian (B1)

Claude Code is a product of Anthropic. Codex is a product of OpenAI.

See what I built with it
numbered decisions
353
engineering gates
51
test files
166

My Work

01Live iOS app

RouteRush

Territory running app for iPhone, live on the App Store: close a loop and the streets inside become yours.

Tools and features

  • SwiftUI
  • Mapbox 3D globe
  • Boldi AI coach

Map data © Mapbox © OpenStreetMap

02Multi-agent content system

Fethiverse

Ten specialised agents research, write, illustrate and review content end to end, across 50+ agent tools.

Tools and features

  • Claude Agent SDK
  • MCP
  • Python
  • TypeScript

03Live Flutter app

Takvapp

A Qur'an and prayer companion for iPhone and Android, co-built in a team of two and live on both stores.

Tools and features

  • Flutter
  • BLoC
  • Prayer times
  • Qibla compass
apps.apple.com

04Agentic RAG

The Faculty

Specialised agents turn source PDFs into exam questions, and a cross-model validator checks every item.

Tools and features

  • Python
  • Gemini
  • ChromaDB
  • RAG
  • Cross-model eval
  • pytest

05RAG chat widget

AI Tutor

Italian-language RAG assistant, deployed to the University of Ferrara course pages, answering with cited sources.

Tools and features

  • TypeScript
  • Fastify
  • React 19
  • Gemini
corsi.unife.it

06Agentic crawl & retrieval

Admissions RAG

An agentic crawl extracts admission rules with evidence checks, feeding a chatbot that cites its sources.

Tools and features

  • Firecrawl crawl
  • Gemini extraction
  • pgvector
  • FastAPI

07Benchmark comparison app

LLMetric

Compares LLMs head to head on a five-axis radar chart, with an AgentQL extraction prototype for new data.

Tools and features

  • Next.js
  • TypeScript
  • Supabase
  • Recharts
  • AgentQL

08Multi-agent marketing agency

RR Ajans

Seven AI agent sessions run RouteRush's marketing like an agency, and a human approves every brief and post.

Tools and features

  • Claude Code
  • Cross-session agents
  • MCP
  • Human approval gates

09Marketing website

RouteRush website

RouteRush's marketing site: a live 3D map you fly by scrolling, in six languages built from one English source.

Tools and features

  • Mapbox GL
  • HTML/CSS/JS
  • Python i18n build
  • Share-link worker
routerushapp.com

My journey &
experience

Mobile & AI Developer

Neurolanche X Labs

2024

Built fine-tuning and end-to-end pipelines, served models on Azure AI and AWS, designed the Flutter app’s backend architecture, and used STT/TTS for live voice chat.

Advanced AI Data Trainer

Outlier

2025

Fine-tuned LLMs alongside AI researchers, ran systematic reasoning and grading evaluations, and built the augmentation and quality-control pipelines behind them.

AI & Full-Stack
Developer

SmartCreative SRL

2026

Moved the design-to-code workflow onto Figma MCP end to end, cutting frontend delivery from days to hours, and built the agentic workflows around the rest of the process.

Open to
opportunities

Available

NOW

Put me on your team and I’ll ship the AI your customers actually need.Hire me

Contact

Availability

Open to opportunitiesHire me

Email

fethiomur@hotmail.com

Location

Torino & Milano, ItalyOpen to relocation