Dominic Stewart is a solutions engineer and technical leader with over a decade of multidisciplinary experience spanning live streaming, XR/immersive production, and web/video platforms. Based in London, he has led cross-functional teams of 7–10+ people, shipped product roadmaps that increased active users by 50%, and moved projects from R&D to production in both the UK and Japan. His career blends hands-on engineering—RTMP/HLS/webRTC, Unity prototyping, Python backend work—with creative production skills in 3DS Max, Maya, and video compositing. Dominic has driven cost and installation optimisations for large-scale installations (including the world’s first permanent holographic theater) and authored voicemail-detection enhancements to an open-source conversational AI framework. Comfortable translating between technical, product and creative stakeholders, he’s equally likely to write SRS docs as to tune a streaming encoder or prototype an AR theatre demo.
6 years of coding experience
6 years of employment as a software developer
Bachelor of Arts (BA), Games Art & Design, 2:1, Bachelor of Arts (BA), Games Art & Design, 2:1 at Norwich School of Art and Design
National Diploma, Interactive Design, National Diploma, Interactive Design at University of Reading
8 GCSEs, Including Mathematics & English, C or above, 8 GCSEs, Including Mathematics & English, C or above at Churchmead School, Datchett, UK
Open Source framework for voice and multimodal conversational AI
Role in this project:
Backend Developer
Contributions:11 reviews, 9 PRs, 1 push in 10 months
Contributions summary:Dominic focused on implementing and refining a voicemail detection example within the Pipecat framework. Their contributions involved modifying and adding Python code within the `examples` directory, specifically targeting a `voicemail-detection` bot. They added new functionality to the voicemail detection to utilize the Google Gemini AI model, as well as updating code for correct dialin and dialout behavior. These changes demonstrate a focus on enhancing the conversational AI capabilities of the Pipecat framework.
Open Source framework for voice and multimodal conversational AI
Contributions:71 pushes, 16 branches in 5 months
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.