I build AI systems and software tools end-to-end, from multi-agent pipelines and LLM integrations to Python backends and automation workflows. My background in cybersecurity shapes how I approach systems: I think carefully about failure modes, reliability, and what happens when things run unsupervised.
Currently completing my MSc in Information Technology at the University of Turku, focused on software design, architecture, and applied AI.
4-agent purple-team copilot built for the AMD Developer Hackathon 2026. LangGraph pipeline transforms MITRE ATT&CK techniques into Sigma detection rules, SOC response guidance, and validation scores. Runs live on AMD Instinct MI300X via vLLM on ROCm. Four simulation modes: Single Technique, APT Group, Kill Chain, and Topology Lab.
AI-driven backend system for ingesting structured and unstructured data, processing it through LLM pipelines, and producing evaluated, structured outputs. Emphasis on reliability, reproducibility, and system-level workflow design.
Multi-agent AI system for Azure infrastructure analysis and cost optimization. Built with deterministic configuration and metrics agents feeding into a Claude-powered supervision layer that synthesizes findings into actionable recommendations. Includes a Streamlit UI for real-time audit orchestration.
Fully local voice assistant built from scratch using faster-Whisper for speech recognition, Ollama for LLM inference, and Piper TTS for voice output. No cloud APIs. Includes a FastAPI web interface with browser microphone support and custom fine-tuned model support via Ollama Modelfiles.
End-to-end Rock Paper Scissors League application built in both TypeScript and Python. The project demonstrates API integration, persistent storage, live updates with Server-Sent Events, validation, and clear backend architecture across two different stacks.
Local-first accounting workspace with two React apps: Ledger (monthly income/expenses, custom columns, JSON export) and Debts (liability tracking, payment logs). All data stored in browser localStorage.
Modular analysis engine for processing and evaluating input data (e.g., logs, traffic, or code), designed for extensible rule-based and automated inspection workflows.
More projects include API tooling, SIEM labs, browser extensions, secure programming labs, and security research.
Designing and building AI-powered systems and backend workflows with a focus on practical applications and local-first architectures. Developing modular pipelines integrating LLMs, APIs, and structured data processing. Building end-to-end projects including voice interfaces and automation platforms.
Building and maintaining web-based applications and developer tools, including browser extensions and full-stack projects. Focus on API integration, system design, and clean, maintainable implementations.
Developed Python-based tools for data processing, monitoring, and workflow automation. Worked with structured data pipelines and system-level integrations.
Analyzed system architectures and networked environments to identify weaknesses and improve reliability. Built scripts and tooling to support analysis workflows and system validation.
Conducted independent analysis of web systems, focusing on identifying implementation issues and validating real-world impact through proof-of-concepts.
Earlier experience and additional roles available on LinkedIn.
