ML / Backend Engineer — I build and ship AI-powered products end-to-end: from data and models to App Store releases and production servers under real load.
- 🤖 LLM in production — built an AI support agent that autonomously resolves customer tickets in a live CRM (RAG over a curated knowledge base, escalation logic, auto-close, safety rails). Running 24/7 with real customers.
- 📱 Multi-platform products — iOS, Android, macOS (Catalyst), tvOS, Windows. Shipped apps through App Store / TestFlight / Google Play review pipelines.
- ⚙️ Backend & infra — FastAPI, PostgreSQL/TimescaleDB, nginx, high-load networking (custom VPN protocols, REALITY/xhttp transports), payment integrations, monitoring.
- 🧰 Automation — Telegram bots ecosystem (sales, support, delivery), ops tooling, ship scripts.
| Project | What it is | Stack |
|---|---|---|
| llm-support-agent | Production LLM agent for customer support (closed source, architecture write-up) | Python, RAG, FastAPI |
| rag-eval-toolkit | Open-source toolkit for evaluating RAG answers with LLM-as-judge | Python |
| vpn-platform | Consumer VPN across 5 platforms: custom tunnel engines, own control plane (closed source, write-up) | Swift, Kotlin, Go, Python |
| tg-commerce-bot | Telegram sales & provisioning bot with payments and web cabinet (closed source, write-up) | Python, aiogram |
- Deepening LLM engineering: fine-tuning, inference optimization, agent reliability.
- Open to ML engineering roles in AI startups.
📫 Contact: goxchief@gmail.com