About

Devin Soni is a highly skilled Machine Learning Engineer with over 7 years of experience in the field. Currently working at Airbnb, Devin has built real-time multi-task deep learning models to detect fraudulent user behavior throughout the user journey, as well as a deep learning NLP model to detect contact information and intention to communicate off-platform. He has also built a graph convolutional network to leverage graph signals in ML models, which was featured in a Medium article. Devin's expertise lies in Python, Java, Scala, TensorFlow, numpy, pandas, scikit-learn, huggingface, XGBoost, and Hive. He has also worked on various projects in ML, Deep Learning, NLP, and software engineering. Prior to his current role, Devin worked as a Software Engineer Intern at Airbnb, where he added new feature definitions to the batch feature processing platform and iterated on supervised machine learning models to identify hosts trying to take guests off-platform. He also worked as a Machine Learning Researcher at Rutgers University, where he worked on a project funded by the NSF to automatically detect cyberbullying using machine learning. Devin holds a Bachelor of Science (B.S.) degree in Computer Science, with a minor in Mathematics, from Rutgers University. He has also published first-author papers accepted to ICWSM and CSCW. Devin's tech stack includes ML, Deep Learning, NLP, Scikit, XGBoost, Pandas, Java, Scala, TensorFlow, Apache Hive, Python, Spark, Redis, Spring, Frontend, and Backend. Overall, Devin is a highly experienced and skilled Machine Learning Engineer who has worked on a variety of projects in the field. His expertise in various programming languages and frameworks, as well as his experience in software engineering and research, make him a valuable asset to any team.