Damian Stewart
Owner at Damian Stewart
Vienna, Austria
Summary
🤩
Rockstar🎓
Top SchoolDamian Stewart is a versatile software engineer with 16 years of experience building full-stack systems, ML training pipelines, and robust tooling for petabyte-scale data and creative AI projects. Based in Vienna, he combines hands-on development—ranging from PyTorch training loops and distributed validation to web UI performance tuning for the widely used InvokeAI—with a strong track record of interdisciplinary collaboration and product-minded engineering. He founded and ran an on-chain generative art platform, architecting blockchain, serverless backend, and frontend systems, and later helped scale infrastructure for web crawl processing used to power foundational LLMs. Known for translating complex technical problems into practical solutions for non-technical stakeholders, he also brings a literary MA and a background in music and game tooling that inform a thoughtful, user-centered approach to software design.
16 years of coding experience
10 years of employment as a software developer
Master of Arts - MA Anglophone Literatures and Cultures, Master of Arts - MA Anglophone Literatures and Cultures at University of ViennaBSc Computer Science Music, BSc Computer Science Music at Victoria University of Wellington
German, maori
Github Skills (17)
pytorch10
artificial-intelligence10
python10
machine-learning10
stable-diffusion10
webui10
huggingface-transformers10
image-generation10
trainings10
ai-image10
ai10
generative-art10
modeling10
javascript9
react9
Programming languages (13)
Github contributions (5)
victorchall/EveryDream2trainer
Jan 2023 - Mar 2023
Role in this project:
ML Engineer
ML EngineerContributions:12 reviews, 58 commits, 45 PRs in 1 month
Contributions summary:Damian primarily focused on enhancing the model training process within the repository. Their contributions include enabling the download of models from Hugging Face, implementing functionality to handle various checkpoint formats, and refining the model loading and sampling procedures. They added features to support distributed training and validation, demonstrating a focus on improving the usability and flexibility of the training pipeline.
invoke-ai/InvokeAI
Nov 2022 - Jan 2023
Invoke is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, and serves as the foundation for multiple commercial products.
Role in this project:Full-stack Developer
Full-stack DeveloperContributions:184 reviews, 71 commits, 72 PRs in 2 months
Contributions summary:Damian made significant contributions to both the front-end and back-end of the InvokeAI project, including implementing UI improvements, fixing bugs, and optimizing image generation performance. They addressed issues related to cross-attention control in the model and also optimized the handling of attention maps. Furthermore, the user worked on improving the stability of the CLI and also contributed to the overall performance of the web UI build.
serveswebuioutpaintingdiffusionlatent-diffusion
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.