Summary
Sudipta Shubha is a PhD candidate in Computer Science at the University of Virginia specializing in cost-efficient, scalable infrastructure for distributed inference of generative AI models. With nine years of experience spanning research and industry, he blends distributed systems, networking, GPU architecture, and ML model expertise to bridge cutting-edge research and production—evidenced by publications at OSDI, SIGCOMM, EuroSys and internships at Microsoft and HPE Labs. His work focuses on practical inference serving for LLMs and agentic AI workloads, optimizing both software stacks and GPU kernels for real-world deployment. Notably, he has a track record of transitioning research prototypes into production systems during industry collaborations, and he contributed earlier to speech recognition research funded by Samsung during his time in Bangladesh. Based in Charlottesville, he brings a researcher’s rigor and an engineer’s pragmatism to large-scale AI infrastructure challenges.
9 years of coding experience
2 years of employment as a software developer
Bachelor's degree, Computer Science, Bachelor's degree, Computer Science at Bangladesh University of Engineering and Technology
Doctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at University of Virginia