Ryan Strauss

I’m an Applied Scientist at Amazon working on large-scale forecasting, uncertainty estimation, and sequential decision-making systems. My research interests center on deep generative modeling, reinforcement learning, and arbitrary conditioning—developing systems that can reason with incomplete information.

I have a track record of first-author publications at NeurIPS and IEEE TVCG, spanning generative models, energy-based methods, and reinforcement learning applications. At Amazon, I’ve translated research concepts into production systems operating at scale, building pipelines that process hundreds of terabytes of data and deploying models validated through rigorous A/B testing.

Previously, I was a graduate student at UNC Chapel Hill working with Junier Oliva in the LUPA Lab, where I developed novel approaches for arbitrary conditioning across VAEs, Transformers, and energy-based models. During my undergraduate years at Davidson College, I worked with Professors Raghu Ramanujan, Michelle Kuchera, Tabitha Peck, and Bryce Wiedenbeck on projects ranging from deep learning for nuclear physics to the first reinforcement learning algorithm for redirected walking in virtual reality.