• File

Даніїл

AI Automation Engineer

Considering positions:
AI Automation Engineer, Data scientist, Python-програміст, монтажер відео, інженер комп'ютерних систем, спеціаліст з впровадження, UI-дизайнер, кодер, Motion-дизайнер
Age:
23 years
City of residence:
Kyiv
Ready to work:
Remote

Contact information

The job seeker has provided: Phone number

Name, contacts and photo are only available to registered employers. To access the candidates' personal information, log in as an employer or sign up.

Uploaded file

Quick view version

This resume is posted as a file. The quick view option may be worse than the original resume.

Danil Krutov
AI Engineer — LLM · RAG · AI Agents · Automation
Warsaw, Poland (Ukrainian) · Remote | [open contact info](look above in the "contact info" section) | github.com/lunev51 | [open contact info](look above in the "contact info" section)

SUMMARY

AI engineer who builds production LLM systems end-to-end — architecture, code, deploy, support. 15+ automation
projects shipped solo since 2024, including four production systems (RAG, vision/OCR, agents, autonomous publishing)
running on real business data. Automation that survives production: rate limiting, idempotency, retries, structured outputs
and cost control by default.

EXPERIENCE

Freelance AI / Automation Engineer 2024 — Present · Remote
Solo, end-to-end delivery for a long-term client (cosmetics manufacturing, under NDA) and small businesses.

Invoice-to-ERP Pipeline — Claude extracts line items from supplier invoices (PDF / scan / photo); Qdrant vector search
matches them against a 4,000-SKU catalog (OpenAI embeddings + fuzzy matching + LLM-as-judge); orders land in 1C ERP in
one click.
Payroll Vision Bot — reads ~200 handwritten payroll sheets per batch with Claude (vision + structured outputs), replacing a
full day of manual entry; custom RPM/ITPM rate limiter and idempotent recovery — nothing lost, nothing duplicated.
Autonomous SMM Engine — Claude generates branded content and publishes to Instagram / Threads / Facebook via the
Meta Graph API, with human-in-the-loop approval.
Agent Workflows — LangChain agent with a Qdrant retrieval tool for cost calculation; Telegram shipment-parser bot; n8n
where it's fast, custom Python / Node where n8n breaks.
15+ earlier projects for small businesses: AI Telegram bots, n8n / API workflow automations, integrations and content
pipelines.

SELECTED PROJECT — OPEN SOURCE

Recipe-costing agent — Claude + Qdrant vector search over 9,285 materials; cuts an estimate from ~30 min to ~30 s at
~$0.05 per run. Fuzzy names → vector retrieval → LLM-as-judge. Code & write-up: github.com/lunev51

TECHNICAL SKILLS

Languages Python, Node.js, JavaScript

LLM / AI Claude & OpenAI APIs, RAG (Qdrant, embeddings), LangChain, AI agents, prompt engineering,
structured outputs, LLM-as-judge, Vision / OCR

Backend / Integrations FastAPI, REST, webhooks, Telegram Bot API, Meta Graph API, Google Sheets API, 1C ERP, serverless
(Vercel)

Automation / Tooling n8n, Claude Code (daily), Git

Reliability rate limiting, idempotency, retries, token / cost control, HITL approval flows

E D U C AT I O N L ANGUAGES

Sumy State University (SumDU) English — B1 (all code & written work in English)
Ukrainian — Native (C2)

Similar candidates

All similar candidates

Candidates at categories

Candidates by city


Compare your requirements and salary with other companies' jobs: