Sohil Grandhi is a Senior Software Engineer at NVIDIA specializing in silicon validation, compiler testing, and automation for complex hardware systems. He previously worked at Intel and Hughes Network Systems, where he contributed to large-scale SoC validation, modem optimization using machine learning, and validation automation frameworks for high-performance computing and communication systems. Sohil holds a Master’s degree in Computer Science and Engineering from Pennsylvania State University and a Master’s in Machine Learning and Artificial Intelligence. He has authored several research papers and book chapters, serves as a journal peer reviewer, and is an active contributor to the technical community and a Senior Member of IEEE.

Open-Source AI and Data Science for Silicon ValidationModern System-on-Chip (SoC) designs generate massive volumes of logs during post-silicon validation, making manual debugging increasingly difficult. This talk explores how open-source artificial intelligence and data science tools can help engineers transform raw validation logs into actionable insights. A practical workflow is presented for collecting, preprocessing, modeling, and analyzing validation data using machine learning and large language models. The session highlights when to apply ML for structured validation data and when LLMs are better suited for unstructured logs and documentation tasks. The talk also introduces emerging generative and agentic AI workflows and discusses how these technologies can support automated debugging pipelines. Emphasis is placed on using AI to augment engineering workflows rather than replace them, enabling engineers to focus on complex reasoning while automation handles large-scale data analysis.