AI Engineer | Agents, Automation & Integrations
Most businesses are already experimenting with AI — but very few are using it the right way.
A generic chatbot is not enough. What actually drives value is a custom AI agent built around your workflows, capable of calling APIs, automating decisions, and integrating directly with your systems. This is where AI stops being a demo and starts becoming infrastructure.
With the right architecture, your AI can handle operations, reduce manual work, and scale processes without increasing costs — from customer support to internal tools, data processing, and beyond.
If you're thinking about building a real AI solution tailored to your business, let’s talk.
2
342
I'm currently building Omnicrm.chat (http://OmniCRM.chat).
A CRM and multichannel communication platform designed to keep customer conversations, sales opportunities, and operational workflows in a single workspace.
Most teams still manage WhatsApp, Telegram, email, proposals, tasks, and customer records across multiple disconnected tools. The result is lost context, duplicated work, and a fragmented customer experience.
With OmniCRM.chat (http://OmniCRM.chat), conversations can evolve into opportunities, projects, and tasks without manual data entry. The goal is to connect communication, CRM, and execution into one platform, while creating a foundation for future AI-driven automation across the entire customer lifecycle.
2
184
Most OCR systems stop at text extraction.
The real value starts after the document is read.
In this project, I built an AI-powered OCR pipeline capable of extracting text from invoices, contracts, reports, and forms while also classifying the document type and identifying key information automatically.
Instead of returning raw text only, the system structures the data into usable outputs for automation workflows, CRMs, ERPs, and AI agents. This reduces manual processing time and makes documents immediately actionable inside business operations.
The stack combines OCR engines with LLM-based processing for contextual understanding, keyword extraction, and intelligent classification. The result is a more reliable document processing flow that can integrate directly with APIs, databases, and automation systems.
This is where AI engineering becomes practical: transforming unstructured files into structured business data at scale
1
280
Java, Angular & Android engineer adding AI to your systems
My own AI assistant for company documents and SQL data. Users ask in plain language and get answers from their files (RAG with LangChain and FAISS) or from their databases (questions turned into SQL queries). Django web app, Python/Flask microservices, OpenAI, Docker.
0
42
WhatsApp AI assistant for an energy company's employees. It answers questions from company documents (RAG with Azure OpenAI and Cognitive Search), adds source links, verifies who is asking before answering and understands voice messages. Python/Flask, Twilio, PostgreSQL, Docker.
1
3
264
