Senior Software Engineer, ML Deployment Optimization

Google's software engineers develop the next-generation technologies that change how billions of users connect, explore, and interact with information and one another.

• Lead the deployment and performance optimization of critical ML models from strategic third-party developers on Google Tensor SoCs.
• Design and implement full-stack (e.g., model architecture, compilers, frameworks, kernels, hardware) optimization strategies, and drive technical analysis and resolution of performance/deployment issues, leveraging ML, systems, and hardware knowledge.
• Architect, design, and develop reusable tools, libraries, and infrastructure to accelerate ML deployment and performance analysis for the broader organization.
• Provide technical leadership and mentorship to junior engineers, and establish/refine best practices, processes, and guidelines for efficient ML deployment on Tensor platforms.
• Collaborate with and influence external partners and internal teams to improve the ML ecosystem and provide feedback for future hardware/software designs, and translate ambiguous customer requirements into technical strategies and roadmaps.

• Bachelor's degree in Computer Science, a related technical field, or equivalent practical experience.
• 5 years of experience with software development in C++ and Python.
• Experience in technical leadership, leading project teams, and setting technical direction.
• Experience in one or more of the following: machine learning deployment, ML frameworks/compilers, performance analysis, computer architecture, embedded systems development, accelerator programming.

• 401k matching
• Health insurance
• Flight privileges
• Stock options
• Flexible work arrangements

Google's mission is to organize the world's information and make it universally accessible and useful.