Chi Wang is an engineering leader and AI infrastructure expert with nearly two decades of experience building large-scale machine learning and distributed systems platforms. He currently works on AI infrastructure and deep learning systems at Salesforce AI, where he has led teams focused on LLM serving, model optimization, distributed computing, notebook platforms, and production AI systems at enterprise scale.
Chi specializes in bridging the gap between cutting-edge AI research and real-world production engineering. His work spans LLM inference and optimization, GPU infrastructure, distributed training and serving systems, observability, data science platforms, and developer tooling for AI applications.
He is the author of Hands-On LLM Serving and Optimization and Designing Deep Learning Systems: A Software Engineer's Guide, where he shares practical insights for engineers building scalable AI systems in production.
Outside of work, Chi is passionate about education, mentorship, and coaching young people in technology and creative problem-solving. He enjoys exploring the future of AI-native software systems and supporting his children’s ski racing adventures around the world.