Tharun Adithya Srikrishnan#
Tharun is member of the Performance and Optimization team within the AI group at AMD. His current work centers on identifying system-level optimizations that enhance the performance of LLM, VLM, VLA and recommendation training workloads. He is also developing efficient model architectures and inference schemes for multi-modal models. Before joining AMD, Tharun spent 6 years as a systems engineer at Qualcomm, where he worked on the world’s first 5G modem chip and developed an accelerator for on-device inference. He holds a Master’s degree from UC San Diego, where he specialized in signal processing and estimation theory. Tharun is a generalist engineer interested in interdisciplinary problems in the semiconductor industry.
Posts by Tharun Adithya Srikrishnan
