Contact information

You can get this candidate's contact information from https://www.work.ua/resumes/10619899/

Work experience

AI Automation Engineer

from 08.2026 to now (3 months)
Self-employed, Дистанційно (IT)

Independent AI engineering projects (document extraction, tool-calling agents, and RAG), built and evaluated end to end. Every project ships with its own evaluation harness, so the numbers below are measured, not estimated.

- Doc to CRM: reads invoices and delivery notes (PDFs or phone photos) into ledger entries, with a review UI for whatever it is unsure about. On 40 documents: 90% fully correct (100% on PDFs, 60% on difficult photos). Human-review routing reaches 88.9% recall with zero false alarms and caught all 5 planted mismatches. Key finding is negative: the model's self-reported confidence was 1.00 on 36 of 40 documents, including ones it got wrong, so routing is driven by cross-checks instead.
- Inbox Agent: a tool-calling agent that triages a queue and stops before anything irreversible. Across 8 evaluation scenarios it picked the correct first tool every time and attempted 6 irreversible actions: 5 were surfaced for human confirmation, 1 was rejected by argument validation, none executed unattended.
- KB RAG Assistant: retrieval-augmented assistant over a private knowledge base, deployed and publicly reachable.

Tech Stack: Python, FastAPI, Pydantic, pytest, Google Gemini, RAG, Docker, Hugging Face Spaces, GitHub Actions.

Automation AI Engineer (n8n/JavaScript/Python) | Full-Stack Developer

from 06.2025 to 07.2026 (1 year 2 months)
Hajus AG, Дистанційно (IT)

Built automation, integrations, and self-hosted Python infrastructure for pan-European e-commerce operations.

- Designed and maintained 350+ workflows in n8n.io and Windmill across 11+ marketplaces (Bol.com, eBay, Mirakl, OBI/VTEX, Metro DE, Praktiker.de, Pigu, Aukro, Okazii)
- Built 5+ production Python micro-services on Coolify (FastAPI/Flask + Playwright + Docker): marketplace publishing, stock sync, UI automation with TOTP 2FA; health-checks, cron, memory limits, GitHub auto-deploy
- Integrated Odoo (JSON-RPC) ↔ Bitrix24 ↔ marketplace APIs into a unified pipeline for orders, invoicing, and delivery confirmation
- Built Pricing Intelligence System: detects negative-margin products, fetches competitor prices via SerpAPI, auto-updates prices with custom JS algorithm
- Developed eBay ↔ Odoo messaging: auto-fetch buyer messages, create support tickets, reply back to eBay
- Implemented AI categorization and content generation (OpenAI, Gemini, xAI Grok incl. Vision) with structured output and fallback chains
- Architected AWS image pipeline (S3 + CloudFront + Thumbor), cut hosting costs by 70%; Bitrix24 error monitoring improved reliability by 40% and cut manual processing time by 60%

Tech Stack: n8n.io, Windmill, Python, JavaScript, FastAPI, Flask, Playwright, Docker, Coolify, Odoo (JSON-RPC), Bitrix24, VTEX, Metro DE, eBay, Mirakl, AWS, OpenAI, Gemini, xAI Grok (Vision), SerpAPI

Front-End Developer (internship)

from 11.2023 to 11.2024 (1 year)
SoftServe, Львів (IT)

- Participated in a volunteer project, gaining hands-on experience with new technologies and delivering projects under tight deadlines.
- Developed user-friendly web applications using HTML, SCSS, and React.js, with backend development in Node.js.
- Managed project version control via Git and automated workflows with GitHub Actions, ensuring seamless collaboration.
- Ensured code quality with SonarQube and performed unit testing using Jasmine, Jest, and React Testing Library.
- Key technologies: SCSS, React.js, Node.js, MongoDB, Git, GitHub, SonarQube, Jasmine, Jest.

Project Engineer

from 06.2016 to 10.2022 (6 years 5 months)
Eco -Techgroup, Львів (Будівництво, архітектура, дизайн інтер'єру)

- Led end-to-end management of engineering projects, including cross-functional team collaboration, site visits, documentation review, and compliance assurance.
- Efficiently handled procurement, budget monitoring, and client/stakeholder communication, ensuring project success and satisfaction.
- Dedicated time to creating drawings, generating business offers, and maintaining communication with clients.

Education

European University

Computer Science (with Honors), Львів
Higher, from 2022 to 2023 (1 year)

I completed a Master's program in Computer Science at the European University, solidifying my theoretical foundation and complementing my practical experience gained through various IT-related projects.

Lviv National Environmental University

Energy and Electrical Engineering Systems, Львів
Higher, from 2009 to 2016 (7 years)

Additional education and certificates

SoftServe Academy - COMPLETE WEBUI ENGINEER COURSE

10/2022-12/2023
Certificate

EF SET English Certificate 57/100 (B2 Upper Intermediate)

2024, травень
Certificate

Angular (ITWDN)

грудень 2023 - лютий 2024
Certificate

IBM Generative AI Engineering Professional Certificate

2026, серпень
Certificate

Generative AI Engineering with LLMs Specialization

2026, серпень
Certificate

Google AI Professional Certificate (Coursera)

2026, липень
Certificate

AI Fluency: Framework & Foundations (Anthropic)

2026, липень
Certificate

Claude Code 101 (Anthropic)

2026, липень
Certificate

Python for Data Science, AI & Development (IBM)

2026, липень
Certificate

AI Agents Fundamentals (Hugging Face)

2026, червень
Certificate

Knowledge and skills

• Стресостійкість
• HTML
• JavaScript
• SASS
• GitHub
• TypeScript
• Bootstrap
• Redux
• React
• CSS
• Node.js
• Figma
• WordPress
• Git
• JQuery
• Webpack
• Gulp
• AI integration
• GenAI
• FastAPI
• Docker
• Python
• N8n
• SQL
• REST API
• PostgreSQL
• AWS IAM
• Playwright
• AWS

Language proficiencies

• English — above average
• Ukrainian — fluent

Additional information

Portfolio: https://portfolio-shamarin-leonid.vercel.app
LinkedIn: [open contact info](look above in the "contact info" section)
GitHub: https://github.com/LeonidShamarin

Automation AI Engineer with production experience in workflow automation, e-commerce integration and self-hosted Python services. Over the past year built 350+ n8n/Windmill workflows and 5+ FastAPI/Flask micro-services for a pan-European multi-brand retailer, with integrations across 11+ marketplaces, cutting image hosting costs by 70%, manual processing time by 60% and improving reliability by 40%.

Now building and evaluating AI systems end to end: document extraction (90% fully correct on 40 real documents, human-review routing at 88.9% recall with zero false alarms), tool-calling agents that stop before irreversible actions, and RAG over private knowledge bases.

Comfortable across the stack: Python backends (FastAPI/Flask), DevOps (Docker, Coolify, Hetzner, Cloudflare, GitHub Actions) and frontend (React, Angular, TypeScript).