# Roman Bellisari

> Design engineer and AI/ML engineer based in New York City. Builds production AI systems, interactive media, and data platforms at the intersection of engineering, design, and machine learning.

Roman Bellisari is a software engineer and designer who works across AI/ML engineering, full-stack development, UI/UX design, and creative technology. He has collaborated with startups, research studios, creative agencies, and major organizations including Google, IBM, Blackstone, Cerberus Capital, Prudential, McCann, Realtor.com, McKesson, and others.

His recent work focuses on multimodal AI systems — building production pipelines that synthesize text, image, video, and voice. He has shipped AI video generation engines, generative interactive experiences, multi-modal storytelling platforms, and ML-driven data systems at scale.

He is especially interested in human-centered design, computational craft, remote sensing, geospatial data systems, and compelling visual experiences.

## Professional Profile

- [About Roman](https://romanbellisari.com/info): Background, experience, and professional overview
- [Work Portfolio](https://romanbellisari.com/work): Software engineering, AI/ML, and design projects
- [Contact](https://romanbellisari.com/contact): Get in touch — LinkedIn, GitHub, email

## Key Projects

- [Realtor.com AI Tours](https://romanbellisari.com/work): AI-driven video generation engine automating property storytelling at scale — multi-modal ML pipeline, FastAPI on Google Cloud Run.
- [Prudential Flash Forward](https://romanbellisari.com/work): Interactive generative AI experience for live events — real-time narrative generation supporting thousands of participants.
- [Patient Storytelling Platform](https://romanbellisari.com/work): Multi-modal AI narrative system for organ transplant patients with multi-language translation.
- [Biography Narration Platform](https://romanbellisari.com/work): AI storytelling platform generating long-form biographies with text, image, voice synthesis, and EPUB automation.
- [The Comma Project](https://commaproject.dev): Data-driven literary analysis — interactive punctuation visualization of 50+ classic novels. Next.js, Framer Motion, GSAP.
- [Sona Mecha](https://romanbellisari.com/work): Urban sound mapping and acoustic inequality research — distributed sensor networks, 3D sound visualization, geospatial data.
- [Cartas.io](https://cartas.io): Computer vision for garment pattern design — pose estimation, 2D-3D reconstruction, diffusion-based synthesis.
- [Ratatouille.nyc](https://ratatouille.nyc): AI recipe generator — Firebase, serverless Python, Vercel.

## Technical Skills

- Languages: Python, TypeScript, JavaScript, SQL
- AI/ML: LLM orchestration, multi-modal pipelines, computer vision, NLP, MLOps, generative AI
- Design: UI/UX design, design systems, interactive media, data visualization, computational design
- Frontend: React, Next.js, TypeScript, Tailwind CSS, Framer Motion, GSAP
- Backend: Python, FastAPI, Node.js, Firebase, serverless architectures
- Data: Apache Airflow, Docker, Azure, Google Cloud, PostgreSQL, ETL pipelines

## Creative Work

- [Photography](https://romanbellisari.com/photography): Photography portfolio
- [Artwork](https://romanbellisari.com/artwork): Drawings and sketches — pigment ink, charcoal, ballpoint pen
- [Objects](https://romanbellisari.com/objects): Physical builds — vintage electronics restoration, motorcycle builds, fabrication

## Optional

- [Bread](https://romanbellisari.com/bread): Sourdough baking project (since 2023)

## Links

- Website: https://romanbellisari.com
- LinkedIn: https://www.linkedin.com/in/romanbellisari/
- GitHub: https://github.com/romanbell
- Are.na: https://www.are.na/roman-bellisari/index