An About Page That Talks Back
This isn’t your average "About" section. It demonstrates a Retrieval-Augmented Generation (RAG) system — an LLM that answers using indexed content about me. It behaves like it’s “fine-tuned on your data” without retraining the base model. Ask about my projects, stack, or experience.
Skills
Languages
- JavaScript
- TypeScript
- Python
- C#
- C++
- PHP
- CSS
- HTML
- Bash
Frameworks
- React
- Angular
- Next.js
- Express
- ASP.NET Core
- FastAPI
- Flask
Runtime / Tools
- Node.js
- NPM
- PNPM
- GitHub Actions
- Docker
- NGINX
- Vite
Automation
- N8N
- Node-RED
- Cron
AI / LLM
- OpenAI API
- DeepSeek
- LangChain
- HuggingFace
- Ollama
AI Automation
I help streamline operations by building custom automation systems powered by AI, APIs, and workflow engines. Whether it’s eliminating repetitive tasks, integrating data across tools, or building logic-driven flows — I create automations that are intelligent, reliable, and scalable.
From simple task triggers to advanced multi-step logic using tools like n8n, Node-RED, or custom Python scripts, I create systems that reduce overhead and let the real people focus on what matters.
Custom LLMs
I develop private, fine-tuned language models based on your unique business data — giving you secure, self-hosted AI that speaks your brand’s voice and understands your domain.
Using frameworks like LangChain, LoRA fine-tuning, and vector stores like ChromaDB, I build intelligent agents capable of answering questions, automating conversations, and reasoning with context — all deployable on your infrastructure or in the cloud.
Want your own ChatGPT-style assistant running on LLaMA, Mistral, or DeepSeek — or using APIs from large models like GPT, Claude, Gemini, or Grok — with full control over behavior, logic, and cost? I can build it from the ground up.