About

Harsha H S is an experienced software engineer with nearly two decades of experience in software design, architecture, development, and testing across a broad spectrum. He has worked on low-level silicon validation, board bring-ups, and device drivers to scalable distributed databases, route planning for autonomous vehicles, and AI applications. Harsha has worked at startups alongside co-founders to bring ideas to life and at MNCs managing geographically distributed cross-functional teams. Currently, Harsha is working as an AI Engineer at Graphcore, where he is working on SDK, involving MLIR lowering of computational graphs and infrastructure for distributed neural network training and inference on Graphcore IPUs based on bulk synchronous parallel processing architecture. He has also improved the CI pipelines and neural network convergence testing infrastructure and provided tools for hardware teams to gather power metrics for various training and inference workloads. Harsha has a strong understanding of AI, Neural Networks, infra, test, Software Engineer, MySQL, and Backend. In the past, Harsha has worked for Amazon as a Senior SDE (Kernel/Hypervisor/Robotics), where he developed a proof of concept for an NX network card emulation in QEMU to remove hardware dependency for the Xen on Nitro program. He has also supervised a small team to deliver the same to include TCP checksum and segmentation offloading. Harsha has also worked for Untangle AI as a Senior Software Engineer, where he delivered products as a core founding team member, aimed at explainable AI for convolution neural networks using signal estimation, uncertainty modeling, and concept extraction, and using Cython to package into SDK and integrated keygen licensing. Harsha has a strong educational background with a BE in Computer Science and Engineering from Vishweshvarayya Technological University (VTU) and a PhD (not completed) in Computer Science and Mathematics from CMI. Overall, Harsha has 17.85 years of relevant experience and a strong understanding of software engineering, AI, and neural networks.