Peter Baylies
Senior Machine Learning Engineer at Canva
Durham, North Carolina, United States
Summary
🤩
Rockstar🎓
Top SchoolPeter Baylies is a Senior Machine Learning Engineer with 11 years of experience blending generative modeling research and practical web engineering, currently working on advanced ML at Canva after contributing to SDXL at Stability AI. He specializes in diffusion models, StyleGAN, PyTorch and embeddings, and has a rare full-stack background stretching from assembly and C/C++ to PHP, WordPress and REST APIs. Peter has shipped production features for high-profile open-source projects like InvokeAI—adding novel sampler options that enhance diffusion sampling—and built backend AI systems for commercial photo-editing products. Based in Durham, NC, he thrives in both rapid prototype teams and large-model development, bridging research-quality model work with robust, scalable backend implementations.
11 years of coding experience
28 years of employment as a software developer
BS Computer Science, BS Computer Science at North Carolina State UniversityNC School of Science & Mathematics
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (6)
diffusion-models10
pytorch10
image-generation10
python10
generative-ai10
machine-learning9
Programming languages (6)
Github contributions (5)
invoke-ai/InvokeAI
Sep 2022 - Oct 2022
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:
Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:5 reviews, 101 commits, 3 PRs in 1 month
Contributions summary:Peter implemented threshold and perlin noise options for Karras samplers, adding new functionality to the diffusion model's sampling process. Their work involved modifying the KSampler and CFGDenoiser classes to include these options, which involved changes to the diffusion model's core functionality. The user also added related parameters to several files, like simplet2i.py and scripts/dream.py.
serveswebuioutpaintingdiffusionlatent-diffusion
pbaylies/stylegan-encoder
May 2019 - Dec 2022
Contributions:35 commits, 6 PRs, 91 pushes in 3 years 7 months
stylegancycleganlatent-spacedeep-learningencoder
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.