Switch to English?
Yes
Переключитись на українську?
Так
Переключиться на русскую?
Да
Przełączyć się na polską?
Tak

Yevhenii N.

Reliable Plus holder
Offer Yevhenii work on your next project.

Spain El Puerto de Santa Mara, Spain
1 hour 41 minutes back
A little busy a little busy
1 arbitration
on the service 10 months 13 days

Rating

Successful projects
No data
Average rating
No data
Rating
372
AI & Machine Learning
88 place out of 2855
Web Programming
1077 place out of 6430

CV

Currently
I work at the intersection of AI prompts, systems prompts, and process automation. I assemble workflows in n8n, integrate services via API + Webhooks (REST/GraphQL/gRPC), add application logic for content and marketing tasks, and automate commercial/business processes.

Experience: 10+ years in marketing and full-cycle content systems (web/product/social media).

Since 2024, I have been participating in parallel on the Outlier (Scala AI, Scala Labs) and Meta AI in the LLM direction - evaluating the quality of responses, optimising prompts, RLHF/SFT on projects (NDA), which gives an advantage for the precise integration/adaptation and optimisation of AI generation in real commercial and production processes.

Tools and stack: n8n, ManyChat, Voiceflow; API/Webhooks; Node.js/TypeScript if logic needs to be added, PostgreSQL, Docker; if necessary - Weaviate/Qdrant+embedding and RAG + ‘memory’

Frontend (currently): React, Refine, TypeScript; Python; i18n (multilingual)

Skills and abilities

Programming

Design & art

Services


Outsourcing & consulting

Writing

Portfolio


  • 17 427 USD

    Mnemostroma

    AI & Machine Learning
    You open a new chat. Explain everything again. The model has no idea what you decided last week. What's blocked. What's off the table. What matters.
    You're not talking to an agent. You're talking to a goldfish with a PhD.
    Mnemostroma fixes that.
    It sits between you and your AI — silent, invisible, always on. You keep working. Mnemostroma watches, learns, remembers.
    Next session? Your agent already knows the context. No prompting tricks. No pasting logs. No "as I mentioned before."
    What it does
    Every time you work with an AI agent, Mnemostroma:
    Catches what matters — decisions, constraints, key facts — automatically
    Compresses it smartly — not a transcript, a distilled memory
    Surfaces it when relevant — without you asking
    Forgets gracefully — old stuff fades, critical stuff stays forever
    Works offline — your memory, your machine, no cloud
    A dual-stream async pipeline (Observer + Content) backed by 5 memory layers and a Formal Hexagonal Architecture — strictly decoupled via Ports and Repository Adapters (SessionRepo, PrecisionRepo) over SQLite WAL. All in ~420MB RAM (baseline) / ~650MB (zoo), ~20ms retrieval.
  • 697 USD

    Context Manager API Service

    AI & Machine Learning
    The core orchestration service for managing AI Agent context, providing a bridge between structured PostgreSQL data and high-performance vector search.

    Features
    Dual-Database Sync: Automatic real-time synchronization between PostgreSQL and Qdrant.
    Local Embeddings: High-performance semantic processing using multilingual-e5-small_Q8 via local TEI.
    MCP Native: Full support for Model Context Protocol to bridge agent memories.
    RESTful API: Secure endpoints built with Fastify for rapid context retrieval.
  • 581 USD

    Amazon Kindle Cookbook — AI pipeline data collection

    AI Content Creation
    Fully automated pipeline for creating a commercial cookbook for Amazon Kindle based on n8n workflow. Result: "Simple Mediterranean Diet Cookbook for Beginners" — 333 recipes, 3-month meal plan, published on Amazon.com.

    What is implemented on n8n
    Recipe collection — automatic parsing and aggregation from sources
    Translation and adaptation — localization for the American market (language, units of measurement, cultural context)
    Nutrient recalculation — automatic conversion and verification of nutritional data
    Formatting — structuring content for Kindle format
    Proofreading and editing — AI-assisted editing to US English standards
    Writing additional chapters — meal plan, snack ideas, wine pairing guide
    Result
    333 recipes
    14-week meal program
    Published on Amazon.com (Kindle Edition)

    Stack
    n8n LLM AI content pipeline parsing translation automation
  • 9294 USD

    fammy.pet - SaaS B2C

    Web Programming
    fammy.pet — AI Food Safety Checker for Pets

    Brief Description
    A service that instantly checks the safety of any food product for dogs and cats. The user inputs the name of the product or ingredient — the system returns a veterinary assessment, detailed composition analysis, and recommendations.

    What has been implemented
    Backend:
    Node.js / Fastify — main server
    200+ endpoints, 7 business functions (2 connected on the front end)
    PostgreSQL — relational database, 30+ tables, 18M+ records and relationships
    Qdrant — vector database for semantic search
    RAG pipeline + Embedding models for AI composition analysis
    Local LLMs for veterinary assessments and comments
    Data:
    Scraped 7 databases (USA + France)
    Products, menus, ingredients, nutrients, veterinary assessments
    n8n — automation of parsing, translation, database status monitoring
    Infrastructure:
    Deployment: Hetzner VPS
    Docker + Coolify
    Supabase

    Stack
    Node.js Fastify Python PostgreSQL Qdrant LLM RAG Embedding Docker Coolify Supabase n8n
  • Range of design work

    AI Art
    #BusinessCards, #booklets, #outdoorAdvertising, #logo, #illustration, #cover, #painting, #AIDesign

Activity

  Latest proposals 8
Freelance project
274 USD
Freelance project
Automation Specialist in WIX
349 USD
AI agent
420 USD
AI Chatbot Developer (Custom + Template Bots) — Long‑Term Remote Work
715 USD
ARTIFICIAL INTELLIGENCE SPECIALIST / AI PROFESSIONAL
350 USD
Correct the mistakes in the work of the AI agent with the vector database.
271 USD
Fine-tuning prompts for the Open AI bot
469 USD