Manish Ravula

Manish Ravula is a Senior Machine Learning Engineer at Apple, where they focus on enhancing LLM inference for speed, scalability, and reliability. Their work includes Apple GPU inference acceleration, distributed inference, and developing production ML pipelines aimed at improving diffusion and multimodal model inference. Previously, they served as an Applied Machine Learning Engineer at Apple, utilizing statistical and ML methods to optimize OS resource management. Manish has also interned at Dell Technologies, where they implemented Python-SQL-R pipelines for battery management, and worked as a Graduate Research Assistant at The University of Texas at Austin, exploring Deep Learning applications in cooperative robotics. Manish holds a Master of Science in Electrical and Computer Engineering from The University of Texas at Austin.