AI AUTOMATION ENGINEER

Gleb Pyatkov

Agentic Workflows & Multi-Agent Systems

I architect and ship production AI systems — multi-agent orchestration, RAG and vector search, fine-tuning and prompt engineering — together with the surrounding software: web interfaces, native macOS (Swift) applications, backend services and infrastructure. AI-native, full-cycle from architecture to operations, delivered solo.

Remote-first · Open to relocation

  • Python
  • LangChain
  • LangGraph
  • RAG
  • pgvector
  • Multi-Agent Systems
  • FastAPI
  • Prompt Engineering
  • Claude Agent SDK
  • MCP
Gleb Pyatkov
gleb_pyatkov.jpg

open to work

6 in production
100% solo, full-cycle
Web + macOS full-stack + native
95% automated
24/7 autonomous
0→1 idea → production

// what I build

Projects

Six production systems — AI agents, automation pipelines and full-cycle SaaS, all shipped solo.

hookora

FLAGSHIP

AI content-marketing SaaS where AI agents run strategy and auto-posting

  • "Brain" multi-agent system — 3 agents (analyst / scriptwriter / closer) sharing a pgvector knowledge base
  • Orchestrated via the Claude Agent SDK; monorepo of 5 services behind one Nginx gateway
  • Fastify + PostgreSQL backend, React 18 + Vite frontend, 43 backend tests, Playwright E2E, Dockerized on a VPS
5 services 3 AI agents 43 tests

stack TypeScript · Fastify · React · Vite · PostgreSQL · pgvector · Claude Agent SDK · OpenRouter · Docker · Nginx

Whispo

0→1 voice-dictation SaaS — macOS + web + payments backend

  • Native macOS app (Swift/SwiftUI) — hotkey dictation (Option+Space), Groq Whisper, paste into the active app
  • FastAPI backend — 13 API modules, JWT (ES256), rate limiting, Prometheus metrics
  • Free/Standard/Pro subscriptions (YooKassa, CryptoCloud), auto-renewal, payment webhooks; GPT-4.1 text cleanup
macOS + Web JWT ES256 Payments

stack Swift · SwiftUI · React · TypeScript · FastAPI · PostgreSQL · Groq · YooKassa · CryptoCloud · Docker

hh.ru Job Agent

CURRENT

Autonomous AI agent that chats with recruiters and applies to jobs for me

  • Claude-based agent across 5 conversation channels (AI recruiter, live recruiter, Telegram, Google Forms, hh.ru forms)
  • RAG retriever over a modular knowledge base — only relevant cards enter the prompt; auto-learns from clarifications
  • Autopilot scheduler, Playwright over SOCKS5, a Telegram userbot (GramJS) and an admin control bot
5 channels RAG Autopilot

stack Node.js · TypeScript · Playwright · GramJS · Claude (MCP, RAG) · Telegram Bot API

MBand

Internal AI platform that cut content production time by 75%

  • 20 backend services with real-time progress over WebSocket/SSE
  • Multiple AI providers (Gemini, Kling, Veo, Topaz, OpenRouter) with load-balancing, retry and fallback
  • Fault-tolerant job queue (memory → DB → file) with auto-recovery; 16-page React SPA
fault-tolerant 20 services −75% time

stack Python · FastAPI · React · TypeScript · FFmpeg · Gemini · Kling AI · Topaz · PostgreSQL · Docker

VikiShop

Fully automated digital-goods store — 24/7, zero humans in the loop

  • 4 microservices (FunPay, Playerok, GGSEL bots + Midasbuy auto-purchase worker)
  • 10-state FSM for the full order lifecycle; Playwright checkout with auto 3-D Secure OTP from email (IMAP)
  • Dynamic pricing; concurrency-safe (SELECT FOR UPDATE), idempotent orders, graceful shutdown
10-state FSM 24/7 Auto 3DS

stack Python · asyncio · SQLAlchemy · PostgreSQL · Playwright · Docker · Telegram Bot API · IMAP

Telegram bots

A series of bots for sales automation, notifications and monitoring

  • python-telegram-bot / GramJS with job queues and inline keyboards
  • Integrated with external APIs and databases; balance monitoring and alerts
  • Admin controls, rate limiting via semaphores, Redis-backed settings
Inline UI Job queue Redis

stack Python · python-telegram-bot · GramJS · Redis · PostgreSQL

// how I work

Approach

An engineer who takes business processes from idea to production with AI agents. I orchestrate LLM agents (Claude Agent SDK, MCP, RAG) and own the whole stack — backend, integrations, frontend, infrastructure and deployment.

  1. AUTOMATION-FIRST

    I design processes around AI agents and multi-agent orchestration, automating up to 95% of manual work.

  2. SOLO, FULL-CYCLE

    From architecture and design to deploy and monitoring — including payments and auth.

  3. AI-NATIVE DEVELOPMENT

    LLM agents at every stage: design, coding, testing, code review.

  4. PRODUCTION-READY

    Every project ships: Docker, health checks, monitoring, error handling, scale.

// stack

Skills & tooling

The stack I use to design, build and ship autonomous systems — end to end.

ai & agents
AI AutomationMulti-Agent SystemsAgentic WorkflowsLLM AgentsLangChainLangGraphLlamaIndexRAGVector SearchEmbeddingspgvectorFine-tuningLoRA / QLoRAHugging FacePyTorchTransformersLLM EvaluationAgent HarnessClaude Agent SDKModel Context Protocol (MCP)Prompt Engineering
backend
PythonFastAPIasyncioSQLAlchemyPydanticNode.jsTypeScriptFastifyREST APIsGraphQLgRPCWebSocketsServer-Sent EventsMicroservices
data & infra
PostgreSQLpgvectorPinecone / QdrantRedisDockerdocker-composeKubernetesNginxCaddyCI/CDAWSPrometheusLinux / VPS
frontend & software
ReactNext.jsTypeScriptViteTailwind CSSZustandReact QuerySwiftSwiftUImacOS apps
automation
PlaywrightTelegram Bot APIGramJSIMAPGoogle Sheets APIFFmpeg

// experience

Experience

Mario Berlucci

Fullstack Developer

Jan 2024 — Present

Footwear & apparel retail brand

  • Built a content-automation platform that cut video processing time by 75% (20+ min → 3–5 min) and automated 95% of manual operations
  • Designed a multi-service architecture — 20 backend services with real-time WebSocket/SSE progress
  • Integrated multiple external AI services with load-balancing, retry logic and dynamic pricing
  • Built a fault-tolerant job queue (memory → DB → file) with auto-recovery and parallel processing of up to 4 videos
  • Set up production deployment — Docker, Caddy reverse proxy with SSL, rsync delivery, health checks

$ contact

Let's build something that runs itself.

Open to AI Automation / Agentic Engineering roles — remote-first, open to relocation.