Full-Stack AI Engineer
I build AI products end-to-end — AI agents, MCP, backend, integrations, launch. One person covering the scope usually split between 3–5 developers.
Honestly — so we don't waste each other's time.
Over 2 years pairing daily with AI agents.
For more than two years I've been working with AI agents as co-authors — I don't just build AI tools, I use them daily in my own workflow.
What this means in practice:
I work with large codebases and complex projects — agents scale execution, I keep the architectural decisions.
Production cases with real clients and code.
An AI assistant that replaces a sales manager in Instagram Direct. Multi-tenant SaaS for salons, barbershops, clinics and solo freelancers — from a single location to networks with dozens of staff. Understands text, photo, voice and video in one conversation. Integrates with CRM (Altegio) and Google Calendar. TOV "MARK1".
Subscription platform for the closed Capitalist Invest / Rynochok investment community. Stripe-bot for payments, Telegram-native admin with 7-step broadcasting, dual-account orchestration, Google Sheets as operational dashboard for the CEO. 500+ members, 800+ webhook events.
A Telegram bot where donors resell shares of a Ukrainian artist's painting to each other. Fundraising for humanitarian demining.
Areas I work in regularly.
Fine-tuning open-source models (Llama, Gemma, Mistral) via PyTorch + Transformers / Unsloth. Integrating commercial models (Claude, GPT, Gemini) via API. Multimodal pipelines (text + image + voice + video). MCP servers, function calling, multi-agent orchestration.
Collecting data from open sources (web, API, datasets). Cleaning, normalization, dedup with pandas / polars. Preparing datasets for fine-tuning — tokenization, JSONL / ChatML formats. Augmentation and synthetic data generation via LLM.
Python (FastAPI, Flask), async pipelines on asyncio + uvloop. Node.js / TypeScript for serverless. REST APIs, webhook ingress. Integrations — Stripe, Telegram Bot API, Meta Graph, Google APIs (Calendar, Sheets, Vertex), Notion.
React 19 + TypeScript, Vite. Tailwind CSS + shadcn/ui for UI. Astro for static sites. Mobile-first responsive, iOS-optimized (safe-area, touch-feedback). Custom UI components from scratch.
CI/CD pipelines (GitHub Actions, GitLab CI). Docker for production deployments — multi-stage builds, docker-compose. Monitoring, backups, secret management via .env / Vault. Logs aggregation.
AWS (EC2, S3, RDS, IAM). Google Cloud (Vertex AI, Compute Engine, Cloud Storage). Cloudflare (DNS, Tunnels, Workers, R2). Hetzner and bare-metal VPS for self-hosted scenarios.
Linux server administration: systemd, nginx, iptables, SSL/TLS. Proxmox virtualization — VM management, snapshots, clusters. Hardware: server builds, BIOS configs, network setup.
Technologies I use to build products and MCP servers.
Not my main thing, but interesting experience too.
I used to work at an ad agency, then ran my own SMM production. With that experience I wanted to build something of my own — and have it actually needed by the market.
In Ukraine there was no quality educational content about DIY equipment repair: big production channels were boring and disconnected from the everyday viewer, while individual mechanics couldn't present complex information in an engaging way. I saw the opportunity and launched MARKUSHA together with my father — a former teacher with his own tricks and achievements in improving agricultural machinery.
After a while millions of views came in along with a stream of thanks in the comments — farmers started upgrading their tractors, combines and other equipment based on our videos. 66% of views from Ukraine, the other 34% — from around the world, from Poland to America.
Glad this project was able to reach this many people and actually help them.
Chat with AI about me using the full context from this site.
Best to message me on Telegram — I respond quickly.