Roosa · Finland · Open to AI, backend, and software engineering roles

AI & Software
Engineer

I ship reliable AI workflows and secure Python backends - designed, tested, deployed, and documented end to end.

I build secure software, AI workflows, and real-time creative tools. At Assembly Summer 2026 I shipped two demoscene projects and placed 2nd in the Fix It Competition with SceneStart. I have been active in the demoscene as an organizer since 2014, and now also as a creator and competitor.

Portrait of Roosa

Selected work

Systems I have built

View all projects →
01

Open-source design engineering infrastructure

ZtotheZ Design Engineering

v2.0.3 · npm and GitHub release

An Agent Skill, MCP server, CLI, and deterministic quality gate for production UI systems.

Turns product intent, interface truth, information hierarchy, architecture, accessibility, and browser evidence into enforceable contracts. Version 2.0.3 includes 20 scoped MCP tools, 168 automated tests, and qualified contained delivery pilots across SceneStart, AegisOPS, and Azure Optimizer.

  • TypeScript
  • MCP
  • Zod
  • Playwright
  • Agent Skills
  • Design systems
ZtotheZ Design Engineering visual
02

Assembly Summer 2026 · Fix It Competition

SceneStart

2nd place · 132 points

Demoscene builder for beginners - export your first real-time browser demo in 5 minutes.

Placed 2nd among 13 finalists at Assembly Summer 2026. Built in 20 hours with 21 learning paths, real-time effects, offline export, and no backend.

  • TanStack Start
  • React.js
  • TypeScript
  • Tailwind CSS
  • Canvas API
Launch SceneStartSource code not yet open source
SceneStart visual
03

Assembly Summer 2026 · AI Coding (Vibe Demo)

Artificial Intelligence Never Sleeps

Real-time audiovisual demo, 122.5 seconds at 1080p60, exploring AI through procedural graphics.

Deterministic 60fps engine with FFT visualization, synchronized narration, procedural effects, and full AI tool disclosure.

  • Python
  • pygame-ce
  • Cursor / Claude
  • FLUX
  • Together Orpheus
  • Suno
Artificial Intelligence Never Sleeps visual
04

AI security automation

AegisOps AI

Public demo

Automates the path from MITRE ATT&CK techniques to Sigma rules, SOC guidance, and validated output.

A four-agent LangGraph pipeline with a Qwen verifier and a public Hugging Face demonstration. A vLLM inference path runs on AMD ROCm hardware.

  • Python
  • LangGraph
  • FastAPI
  • vLLM / ROCm
  • MITRE ATT&CK
AegisOps AI visual
05

Production delivery

Pipe Production & Inventory

Confidential client

A delivered production system connecting work orders with pipe and material inventory.

Includes stock deduction, remnants, audit trails, authentication, health checks, handover documentation, and Linux deployment. Client details remain confidential; the repository is a sanitized demonstration.

  • FastAPI
  • React
  • PostgreSQL
  • Linux
Pipe Production & Inventory visual
06

Evaluated RAG

AI Insight Engine

Public repository

RAG-assisted Python security auditor with citations and reproducible evaluation.

Backed by 20,875 embeddings and a documented 15-case evaluation suite, with FastAPI, pgvector, pytest, and GitHub Actions CI/CD. Baseline results and failure analysis remain public in the repository.

  • RAG
  • pgvector
  • pytest
  • CI/CD
AI Insight Engine visual

How I build

Software engineering, creative coding, and AI

I combine a cybersecurity-informed engineering approach with web development, educational technology, and real-time graphics. Validation, visible failure modes, deployment, and handover remain part of the system - not afterthoughts.

  • React.js
  • TypeScript
  • Python
  • Canvas API
  • Web Development
  • TanStack Start
  • Tailwind CSS
  • Real-time graphics
  • Procedural generation
  • Educational technology
  • MCP / Agent Skills
  • Design engineering

Web applications

React.js, TypeScript, TanStack Start, Tailwind CSS, and browser-native APIs.

See SceneStart

Creative coding

Canvas API, real-time graphics, procedural generation, synchronized audio, and 60fps rendering.

See the Assembly demo

AI & reliable systems

Python, LangGraph, RAG, testing, structured outputs, local inference, and deployment.

See AegisOps

Awards & honors

Assembly Summer 2026

Fix It Competition - 2nd Place

SceneStart earned 132 points and placed second among 13 finalists at Assembly Summer 2026.

Try SceneStart ↗

AI Coding (Vibe Demo) Competition

Competed at Assembly Summer 2026 with Artificial Intelligence Never Sleeps, a disclosed AI-assisted real-time audiovisual production.

View on Demozoo ↗

Experience

Where I have worked

Oct 2024 - Present

Independent Software & AI Engineer

AI engineering focus since January 2026

Building design-engineering infrastructure, AI workflows, backend applications, and deployment-ready tools from system design through testing and documentation. Work includes MCP tooling, multi-agent security automation, RAG evaluation, local-first AI, and confidential client delivery.

Sep 2023 - Feb 2026

Personal Care Assistant

Mehiläinen

Worked independently in a regulated home-care setting where reliability, discretion, and clear communication with non-technical clients were essential.

Jan 2022 - Sep 2024

Systems & Security Consultant

Santa Monica Networks

Analyzed system architectures and networked environments to identify weaknesses and improve reliability. Built scripts and tooling for analysis workflows and system validation.

Nov 2019 - Jan 2020

Junior Python Developer

NetNordic Finland

Built Python tools for data processing, monitoring, workflow automation, and system-level integration.

Oct - Nov 2019

Junior SOC Analyst

NetNordic Finland

Log analysis, documentation, and security monitoring support.

Additional technical activity: independent security research from 2018 to 2026, including web-system analysis, proof-of-concepts, and public security tooling. Earlier roles and additional detail are available on LinkedIn.

Education

Formal background

In progress · expected 2027–2028

Master of Science (Technology)

University of Turku · Information Technology

  • Robotics and Autonomous Systems specialisation
  • Multidisciplinary AI Module, 47 credits

Graduated May 2021

Bachelor of Engineering

Turku University of Applied Sciences · ICT

  • Data Networks & Cybersecurity specialisation
  • White Hat Hacking thesis, graded Excellent

Selected recent learning: AMD Developer Hackathon completion · Google AI · IBM Generative AI

Languages: Finnish (native) · English (professional) · Norwegian (elementary)

Professional recommendations

Recommended by colleagues and instructors

View on LinkedIn ↗
“Roosa’s knowledge of IT security and her skills are something to be amazed at. A hearty recommendation.”

Mikko Väisänen

Chief Information Security Officer, theFIRMA

Same-team colleague ·

“Roosa is a bright individual; she had no trouble at all at passing her courses with the highest grades. Also, she is a delight to work with.”

Vesa Slotte

Cisco Networking Academy Instructor

Former teacher, Turku University of Applied Sciences ·

Contact

Open to AI and Python engineering roles

Based in Finland and available for AI, backend, and software engineering roles, on-site in the Turku region or remote. Email is the quickest way to reach me.

contact@ztothez.com

Messages sent to contact@ztothez.com are used only to respond to your enquiry.