My research lies at the intersection of artificial intelligence and computer systems, with a focus on designing scalable and efficient systems, including architecture, compilers, runtime environments, and distributed infrastructure, for AI applications. I also work extensively on natural language and conversational AI systems, with an emphasis on deploying data-driven models and systems in real-world enterprise environments.
To support these efforts, I develop and leverage a wide range of data science tools and methodologies, including model profiling, performance modeling, workload characterization, and large-scale data processing pipelines. My research emphasizes co-design across the AI stack, from hardware to software, to optimize training and inference for modern deep learning workloads.
I have published over 40 papers at leading venues in computer architecture, systems, and AI (including ISCA, ASPLOS, MICRO, and ACL), and have received recognition through awards such as the Google Research Award, Facebook Research Award, J.P. Morgan Faculty Research Award, the ISCA/ASPLOS/MICRO Hall of Fame, and the NSF CAREER Award. I have graduated 11 Ph.D. students and mentored 7 postdoctoral fellows, many of whom now lead research efforts in academia and industry.