Software Developer & Systems Specialist @Vention
Co-founder of @VICAMOS, an AI-automated security system for businesses and industrial sites.
Specialized inArchitect and deploy distributed systems · Run and manage inference on NVIDIA A30s · Build containerized worker pipelines in Go · Handle high-throughput media processing with ffmpeg & RabbitMQ · Optimize Linux environments for performance, reliability, and cost.
Tech I enjoyGo · TypeScript · Bash · PostgreSQL · Docker · Nginx · ffmpeg · Ubuntu · Pinecone
Building internal AI proof-of-concepts, automation workflows, and semantic data tools for client-facing products at an international software company. Collaborating with distributed teams across Europe, including Poland, Germany, and Lithuania. Also provisioned NVIDIA A30 inference infrastructure and led practical AI workshops across the company.
Built React applications, testing workflows, and internal tools for media and subscription products. Work included Storybook/Chromatic CI, Jest/Cypress coverage, a Vue-to-React migration, and AI-assisted research tooling for Der Spiegel.
Brief engagement with an international software consultancy during a relocation within Europe. The role ended almost immediately due to the war in Ukraine and the resulting sanctions, which disrupted the company's operations in the region.
Built and shipped frontend features with React, TypeScript, and Next.js while coordinating directly with design and product stakeholders. Focused on performance, code quality, Lighthouse improvements, and weekly client delivery.
Created frontend systems and reusable UI foundations with React, Storybook, ESLint, and Prettier. Improved performance through lazy loading, asset optimization, and Lighthouse-focused delivery.
Delivered a frontend project across design, implementation, SEO, and performance work. Used Figma, Zeplin, Tailwind CSS, Jest, and GitHub Actions to keep the product shippable and maintainable.
VICAMOS is an AI-automated security system that monitors sites, identifies threats, and responds automatically based on the owner's security rules. It combines cameras, alerts, and incident reports in one platform, with access through the browser and mobile apps.
DispatchPing turns field-service planning from spreadsheet work into optimized weekly schedules. It matches jobs to technicians by location, certification, time window, and SLA, then produces route maps, timelines, and field-ready exports.
PodZeus made podcast archives searchable by exact moments, using transcription, timestamps, lexical search, and semantic search to help creators and advertisers find relevant clips. The product generated revenue before being discontinued in August 2026.
ClipZeus analyzed YouTube videos for short-form clippers, helping identify high-potential moments from long-form content. The project was paused after YouTube API and bulk-download restrictions made video ingestion at scale impractical.
ChefGPT generated country-specific recipe collections with OpenAI, turning prompt output into a browsable recipe site. It was a small experiment in AI-generated content, formatting, and export-ready recipe pages.
