Transforming AI from experimentation to production-ready systems
Engineering-first approach to intelligent automation.
AI-Driven Automation & Intelligent Workflows
I specialize in artificial intelligence-driven automation and the design of intelligent workflows that connect software systems, data, and decision-making processes.
My work focuses on building practical, production-ready solutions using tools such as n8n to automate complex workflows, orchestrate APIs, and integrate AI capabilities into existing systems. I make extensive, professional use of modern AI assistants and developer tools — including ChatGPT, Claude, Claude Code, GitHub Copilot, Google AI Studio, and Google Labs — to accelerate development, improve code quality, and support advanced problem-solving.
RentMate
Coming soon.
SyndicAI
Coming soon.
Modern AI Tools & Assistants
Professional integration of cutting-edge AI development tools to accelerate software delivery and enhance code quality. I leverage ChatGPT, Claude, Claude Code, GitHub Copilot, Google AI Studio, and Google Labs as integral parts of my engineering workflow — not just as assistants, but as force multipliers for problem-solving, code generation, and system design.
These tools enable rapid prototyping, intelligent code completion, automated testing scenarios, and sophisticated debugging capabilities that dramatically improve development velocity while maintaining high quality standards.
Intelligent Workflow Orchestration
Building complex, automated workflows using n8n and similar orchestration platforms to connect disparate systems, automate decision-making processes, and integrate AI capabilities seamlessly into existing infrastructure.
From API orchestration to data pipeline automation, I design workflows that are maintainable, scalable, and production-ready — ensuring that automation delivers real business value, not just technical demonstrations.
Local & Edge AI Deployment
Beyond cloud-based AI, I actively work with local and edge AI setups, bringing intelligence closer to the data source and enabling privacy-preserving, low-latency AI applications.
- Hugging Face LLMs: Installing and running large language models locally for maximum control and privacy
- NPU-Enabled Hardware: Deploying models on specialized neural processing units for optimal performance
- Raspberry Pi 5 Edge AI: Experimenting with and optimizing LLM deployments on edge devices, pushing AI capabilities to resource-constrained environments
Model Context Protocol (MCP) Solutions
Designing and implementing Model Context Protocol (MCP)-based solutions that enable structured interaction between AI models, tools, and workflows. This approach provides more reliable, controllable, and auditable AI behavior in real-world applications.
MCP allows for sophisticated orchestration of AI capabilities, enabling context-aware decision-making, tool usage, and multi-step reasoning while maintaining transparency and control over AI operations.
Engineering-First Philosophy
My approach to AI is engineering-first: I focus on robustness, automation, and real business value rather than experimentation alone. The goal is always the same — turn AI into a dependable system component, not just a standalone feature.
This means prioritizing production readiness, maintainability, observability, and integration with existing systems. AI solutions should be reliable infrastructure, not fragile prototypes.