The role focuses on designing and implementing software for AI infrastructure, specifically connecting Tensor Processing Unit (TPU) clusters and cloud systems. It involves building and integrating cloud compute software to support AI development and deployment at scale.

Senior Software Engineer for Google Home Camera, focusing on the camera stack and On-Device Machine Learning (ODML) framework for AI home security products. Responsible for end-to-end ownership of NPI projects, advancing computing technologies for consumer devices, and providing technical coaching.

Senior Software Engineer role focused on developing firmware and software for Google's custom AI accelerators (TPUs). The role involves designing and building low-level C++ code for embedded micro-controllers on ASICs, co-designing hardware/software interfaces, developing tools for ASIC bring-up and debugging, building simulators, and architecting telemetry systems for monitoring TPUs. This position is crucial for enabling the development and scaling of AI models and infrastructure at Google.

Software Engineering Manager responsible for leading a team that develops system software and networking technologies for GPU-based AI/ML supercomputers in Google's data centers. This includes managing engineers, defining technical roadmaps, and overseeing the integration, testing, deployment, and debugging of system software for accelerator products.

Senior AI System Engineer role focused on influencing Tensor SoC architecture for AI/ML workloads on Pixel devices. This involves cross-functional collaboration with SW/HW architects and research teams to optimize for Power, Performance, and Area (PPA) trade-offs, enabling advanced Generative AI experiences. The role requires a data-driven approach using profiling, simulation, and modeling to define future SoC architectures and system design documentation.

Software Engineer III role focused on building and integrating Cloud Compute software to bootstrap TPU AI Infrastructure, including OS image deployment and node-specific software for computation offload, integrating with TPU clusters and cloud infrastructure. The role involves collaboration with TPU Software and Hardware teams and partnering with cross-functional leaders to shape ML infrastructure.