Denis Dmitriev
AI Builder & ITAM Veteran
21 years of data pipelines and compliance engineering — now applied to building with AI, running local LLMs, and shipping AI-assisted software end-to-end.
// about
From IT Asset Management → Building with AI
Twenty-one years engineering data pipelines, compliance reporting, and integration plumbing for enterprise ITAM platforms — Snow, Flexera, IBM QRadar, OpenAI, Power BI. Every project was variations on the same theme: extract messy data, encode domain rules, ship something automated that holds up at audit-grade quality. That instinct turned out to be exactly the foundation modern AI work needs.
Around 2024 I went deep into AI hands-on: built a home GPU cluster running Ollama, ComfyUI, and OpenWebUI on five NVIDIA cards (≈104 GB VRAM). Started using Claude Code CLI as my primary IDE — not as an assistant on the side, but as the way I write software. The portfolio you're reading was built that way. So was the n8n LinkedIn auto-publisher behind dmt-lab.nl. So was a microservices algorithmic-trading platform running 24/7 on dedicated hardware.
What I build now sits at the intersection of two things I already knew how to do well — data pipelines and enterprise integration — and one I learned by stress-testing it: practical AI engineering. Running models locally to understand their failure modes. Using SaaS LLMs cost-efficiently. Writing prompts that hold under production load. Designing AI workflows that don't drift between releases. The same engineering discipline I brought to license compliance, now applied to systems where the data sources are tokens and embeddings.
// journey
My Tech Journey
2026
ai.dmt-lab.nl
AI Portfolio Site
Built with Claude Code
This site. New companion portfolio focused exclusively on AI work. Cloned and refactored from dmt-lab.nl in a single Claude Code session — same Bee Hive theme, separate content track, separate contact pipeline, separate Docker deploy on the shared Contabo host.
2026
n8n LinkedIn Auto-Publisher
AI-Collaboration Build
Self-hosted on Contabo
Designed and shipped a Mon/Thu cadence content pipeline: PostgreSQL queue → n8n workflow → LinkedIn Posts API with 3-step image upload, escape-rule handling, and first-comment URL placement. Built with Claude Code as primary collaborator; the build story itself became a portfolio piece.
2025–2026
Home AI Lab
Local LLM Infrastructure
Slovenia
Built a multi-GPU AI rig — 5 NVIDIA cards (2× RTX 3060, RTX 4060, 2× Tesla V100-SXM2-32GB), ≈104 GB VRAM total — running Ollama, ComfyUI, OpenWebUI. Used to stress-test 20+ open models, build custom image pipelines, and understand AI capabilities by pushing them to failure.
2024–2026
Algorithmic Trading Platform
24/7 Microservices System
Dedicated hardware
Hybrid Python/FastAPI + Node.js/TypeScript platform: multi-timeframe data collection, confluence scoring, WebSocket execution, isolated Docker zero-trust topology, React control panel. Written almost entirely in pair with Claude Code over 40+ planning iterations.
2024
ChatGPT Enterprise Compliance Connector
AI Meets ITAM
Enterprise client
First production project bridging an AI vendor (OpenAI) with traditional ITAM tooling (Snow License Manager). Python connector against the OpenAI Compliance API, pandas enrichment, SQL Server stored procedures, retry-with-historical-fallback after diagnosing transient API gaps causing false license revocations.
2004–2024
20 years in IT & ITAM
The Foundation
Moscow → Germany → Slovenia
Rosbank/Société Générale (HP BSM, ITSM architecture, monitoring) → COMPAREX → SoftwareOne → freelance (Snow, Flexera, Oracle Java, ToolsHub24). Two decades of data pipelines, compliance reporting, and enterprise integration — the discipline that translates directly to making AI usable at production quality. Full ITAM portfolio at dmt-lab.nl.
// projects
AI Projects
Three tracks of AI work. Applied AI — bringing AI vendors into enterprise ITAM systems where they didn't exist before. Built with AI — production software shipped collaboratively with Claude Code as primary IDE. Local AI Lab — hands-on infrastructure to understand model behavior at the metal.
The thread connecting all three: the same data-pipeline and compliance-engineering discipline that defined two decades of ITAM work, now applied to systems where the inputs are tokens, embeddings, and probabilistic outputs.
Client-touching work anonymized for confidentiality. Personal projects fully detailed.
ChatGPT Enterprise Compliance Connector
An enterprise had deployed ChatGPT broadly — hundreds of users, real daily usage — but their ITAM platform (Snow License Manager) had no native connector to OpenAI. The SAM team couldn't answer basic compliance questions: who's actually using it, who hasn't logged in for months, what should be reclaimed.
This Site — Bee Hive Portfolio Built with Claude Code
Needed a focused AI portfolio separate from dmt-lab.nl, sharing the same Bee Hive design system but with its own seven-section content track, its own contact pipeline (subject-tagged to distinguish AI inquiries from ITAM ones), and its own Docker deploy on the shared Contabo + Nginx Proxy Manager host. Manual scaffolding would have been a weekend; the goal was to do it in one focused Claude Code session.
n8n LinkedIn Auto-Publisher — AI-Collaboration Build
dmt-lab.nl had 12 substantive technical articles sitting unread because nothing was driving traffic. Manual LinkedIn posting at the cadence needed (Mon/Thu 09:00 for compounding visibility, distinct 24-hour engagement windows per post) would have meant 6-10 hours of upfront work plus ongoing willpower. SaaS schedulers don't integrate with the blog DB, the OG metadata, or my image library.
Home AI Lab — Local LLM Infrastructure
Wanted to understand AI capabilities and failure modes hands-on, not just by reading benchmarks. Running models on a SaaS API doesn't teach you what happens when the GPU runs out of VRAM mid-inference, when a quantization choice flips a model's reasoning behavior, or when ComfyUI graphs hit a memory wall on multi-pass image generation.
Algorithmic Trading Platform — Microservices Built with Claude Code
Wanted a 24/7 production-grade system to stress-test what AI-assisted development can actually ship — not a toy prototype. Real risk controls, real WebSocket execution, real audit trails. The architecture mirrors what I build professionally for license compliance (multi-source data pipelines, systematic decisioning, audit logs), just in a higher-stakes domain.
Ideogram 3.0 LinkedIn Image Pipeline
Every LinkedIn post for the auto-publisher needs a unique 1200×1200 visual matching the Bee Hive aesthetic — terminal-green-on-black or warm-paper-white-on-charcoal, amber/honey accents, no logos, technical motif tied to the article topic. Doing 14 by hand in Figma or Photoshop is a half-day per image. Default AI image generators produce generic stock-looking results that don't match the site's voice.
// skills
Skills & Technologies
Four skill clusters — three about AI, one anchored to the 20+ years of data-pipeline and integration work that makes them usable in practice.
LLM Engineering
Building with frontier and local models — knowing where each one fits
- Claude API / Anthropic SDKPrompt design, tool use, context engineering
- OpenAI APICompliance API, GPT integration patterns
- OllamaLocal model inference across multiple GPUs
- ComfyUIImage-generation pipelines, custom node graphs
- OpenWebUIInterface layer for local LLM stacks
- Ideogram 3.0Prompt-engineered image generation at production scale
AI-Assisted Development
Software written with AI as primary collaborator, not autocomplete
- Claude Code CLIPrimary IDE for Next.js, Python, Node.js, n8n
- Agent orchestrationMulti-step coding loops, planning, code review
- Spec-driven devSource-of-truth docs that drive code, content, copy
- Test-driven AI workflowsLocking behavior with tests before extending
AI Workflow Automation
Self-hosted automation pipelines for content, data, and integrations
- n8nOAuth, cron, retries, PostgreSQL-backed queues
- LinkedIn Posts APIMulti-step image upload, escape rules, comments
- PostgreSQL queue designStatus state machines, position ordering
- Docker on shared infraNPM, Cloudflare, shared external networks
Foundations (anchored to 20+ years of ITAM)
The data engineering discipline that makes AI usable in enterprise
- Pythonpandas, sqlalchemy, FastAPI — same toolkit, new domain
- SQL Server / PostgreSQLT-SQL, stored procedures, schema design
- Data pipelines & ETLAPI → transform → import, retry & fallback patterns
- Linux / Docker / ProxmoxMulti-node home lab, GPU passthrough, networking
- REST API integrationOAuth, pagination, rate-limit handling
- ITAM backgroundSnow, Flexera, Power BI — see dmt-lab.nl for that track
// blog
Blog / Articles
Build-story write-ups from the AI projects — Claude Code workflows, local LLM lessons, and AI-meets-ITAM integration patterns.