Cristina Segalin — Software Engineer

I work at the intersection of Machine Learning, Computer Vision, Generative AI, and Multimodal Perception, building intelligent systems that expand human creativity. My research focuses on developing AI models that act as creative collaborators — systems that perceive, understand, and synthesize visual, temporal, and social signals to enable new forms of expression. I am currently a Senior Research Software Engineer at Google, on the Creative Camera team, where I develop next-generation camera AI systems that integrate perception, generative modeling, and multimodal understanding. My work explores how foundational vision and generative models can power real-time creative tools, bridging capture and creation through scalable, data-driven ML systems. Previously, I was a Tech Lead at Adobe Firefly, leading large-scale data curation and content moderation pipelines powering generative video foundation models. I drove end-to-end initiatives — from problem definition to production deployment — working at the intersection of model architecture, multimodal understanding, and high-quality dataset design to enable production-ready video diffusion systems across Adobe’s creative applications. At Netflix, I built and deployed large-scale computer vision and machine learning systems to support content creation workflows across art, animation, VFX, and games. My work spanned research, experimentation, A/B testing, and production deployment, including generative systems inspired by state-of-the-art diffusion and multimodal architectures. At Disney Research, I designed perception-driven ML systems to create interactive and immersive experiences across theme parks, resorts, and cruise ships. I bring 8+ years of experience developing and commercializing AI/ML systems, including 5+ years leading cross-functional technical initiatives. My work has resulted in 20+ peer-reviewed publications, 10+ invited talks, multimedia coverage, and 1 patent, with publications in venues including IEEE Transactions on Affective Computing, CVIU, CVPR, ACM Multimedia, and ACCV.

Stackforce AI infers this person is a Media & Entertainment AI Specialist with a focus on Computer Vision and Machine Learning.

Location: New York, New York, United States

Experience: 17 yrs 2 mos