Zak Costello
About Zak Costello
Zak Costello is a Senior Machine Learning Scientist at Generate Biomedicines, Inc., where he focuses on synthetic biology and machine learning. He has published work in prominent journals and has extensive experience in research and development across various institutions.
Work at Generate Biomedicines
Zak Costello has been employed at Generate Biomedicines, Inc. since 2022, currently holding the position of Senior Machine Learning Scientist. His role involves applying machine learning techniques to solve complex problems in synthetic biology. Prior to this, he worked as a Machine Learning Scientist II from 2021 to 2022 and as a Machine Learning Scientist from 2019 to 2021. All his roles at Generate Biomedicines have taken place in Cambridge, Massachusetts.
Education and Expertise
Zak Costello earned his Doctor of Philosophy (Ph.D.) in Electrical Engineering from Georgia Institute of Technology, where he studied from 2011 to 2015. He also holds a Master’s degree in Electrical Engineering from the same institution, completed from 2011 to 2013, and a Bachelor’s degree in Electrical Engineering, achieved from 2005 to 2009. His educational background equips him with a multidisciplinary skill set, including machine learning, control theory, applied mathematics, and robotic automation.
Background
Prior to his current position, Zak Costello worked in various roles that contributed to his expertise in machine learning and synthetic biology. He served as a Postdoctoral Fellow at the Joint BioEnergy Institute from 2016 to 2019. He also held positions as a Graduate Research Assistant and Research Engineer I at Georgia Tech and as an Undergraduate Research Assistant at The Johns Hopkins University. His diverse experiences have shaped his approach to solving challenges in synthetic biology.
Achievements
Zak Costello has published work in prestigious journals, including Nature Communications and IEEE Transactions on Automatic Control. He co-authored a research article on Chroma, a generative model for protein design. His contributions include developing a diffusion process for protein design and creating an efficient neural architecture for molecular systems based on random graph neural networks. He has also been acknowledged for his assistance in developing experimental and computational methods using MIT's resources.