About Portfolio Services Blog Contact
EN DE RU
Let's talk →
About

I build AI systems that
actually work
in production.

Denis Shokhirev. Enterprise AI Systems Architect based in Erlangen, Bavaria. Five years building and shipping autonomous agents, RAG pipelines, and Computer Vision systems for DACH B2B — from proof of concept to production deployments.

Denis Shokhirev — Enterprise AI Systems Architect
Denis Shokhirev
Erlangen, Bavaria · Germany
5+
Years in AI
9+
Systems Shipped
1
Rospatent Patent
3
AI Agents Active

My story

From automation scripts
to enterprise AI systems

2020

First automation. First client.

Started with Python automation scripts for small businesses. Quickly realized the bottleneck wasn't code — it was architecture. Built the first RAG prototype connecting 3,000+ documents to a custom retrieval layer. Client cut document search time from 40 minutes to 8 seconds.

2022

Computer Vision for industrial use

AirConductor — gesture-controlled presentation software using MediaPipe + Python. Replaced the Bluetooth clicker entirely. This opened the door to DACH B2B industrial clients needing vision systems for quality control and production monitoring.

2024

Rospatent software patent

NextGen Pathways — AI-driven career guidance system — received Rospatent software certificate №2025612789. First patented algorithm in the portfolio. Demonstrated that the architecture was not just practical but legally protectable IP.

2025–2026

DennisCraft AI Studio — autonomous infrastructure

Founded DennisCraft AI Studio. Built OpenClaw — a 24/7 AI orchestrator managing 9 projects in parallel via Telegram. Three AI agents coordinate through a shared file-system pipeline. Zero VC. Zero outside capital. All revenue from B2B client projects.


Core expertise

What I actually build

🤖

Autonomous AI Agents

Multi-step reasoning pipelines that act without human intervention. LangGraph, custom tool-calling, retry logic, state management. Production-grade orchestration.

LangGraphOpenAI APIAnthropicTool-calling
🔍

RAG Pipelines

Retrieval-Augmented Generation with semantic search over private documents. Qdrant/Pinecone vector stores, chunking strategies, reranking, hybrid search.

QdrantLlamaIndexEmbeddingsHybrid Search
👁️

Computer Vision

Real-time object detection, gesture recognition, industrial quality control. YOLOv8, MediaPipe, OpenCV. Runs on edge hardware, not just cloud.

YOLOv8MediaPipeOpenCVEdge AI
⚙️

Agentic Workflows

LLM-driven business process automation. Email classification, document extraction, CRM integration, automated reporting. End-to-end pipelines.

Pythonn8nZapier AIREST APIs
📊

AI Infrastructure

Production deployment on Hetzner/AWS/GCP. Docker, monitoring, logging, cost optimization. Runs 24/7 without babysitting.

DockerSupabaseKoyebFirebase
🧠

LLM Fine-Tuning

Custom model adaptation for domain-specific use cases. LoRA/QLoRA fine-tuning, PEFT, evaluation frameworks. Deploy locally with Ollama.

LoRAQLoRAOllamaTransformers

Architecture

How I design AI systems

Agentic AI Architecture — DennisCraft AI Studio 2026
Agentic AI Architecture · 2026 DennisCraft AI Studio

Stack

Tools I trust in production

AI / LLM
OpenAI GPT-4.1
Claude Sonnet 4
Gemini 2.5 Pro
Grok
Qwen 3 (local)
LangChain
LlamaIndex
LangGraph
Computer Vision
MediaPipe
YOLOv8 / Ultralytics
OpenCV
PyTorch
TensorFlow
ONNX Runtime
Backend / Infra
Python 3.12 + uv
FastAPI
aiogram 3
Docker
Supabase
Firebase
Koyeb
Data / Vector
Qdrant
Pinecone
PostgreSQL
Redis
Pandas
NumPy
Jupyter

Credentials

Verified milestones

🏆
Rospatent Software Certificate
№2025612789 — NextGen Pathways AI System
🏢
DennisCraft AI Studio
Registered company, Erlangen, Bavaria, Germany
📍
DACH B2B Focus
Germany, Austria, Switzerland enterprise clients
📺
YouTube Channel
@ger_dennis_ai — AI architecture content
✈️
Telegram Community
@ger_dennis_ai — 24/7 AI system updates
Connect

Let's work together

I work with DACH companies that need AI systems that actually function in production — not demos, not prototypes. If you have a real problem, I have a real solution.

Send a project brief →