The Software Engineer role in the GDC AI Models and Performance team at Google focuses on enhancing LLM serving and optimizing GPU performance. Engineers will work on advanced serving architectures and contribute to disaggregated serving initiatives. This position requires collaboration with various teams to ensure efficient deployment of LLMs in production. The role offers an opportunity to innovate in AI infrastructure and improve performance metrics.

• Bachelor’s degree or equivalent practical experience.
• 8 years of experience in software development.
• 5 years of experience testing and launching software products.
• 3 years of experience with software design and architecture.
• 5 years of experience with ML design and ML infrastructure.

• Design, develop, and implement enhancements to the LLM serving stack.
• Contribute to the design and implementation of advanced serving architectures.
• Build and maintain infrastructure and tooling for performance analysis of LLM models.
• Identify and address performance bottlenecks across the stack.
• Collaborate with research, engineering, and SRE teams to optimize LLMs in production.

• Employees at Google are often offered benefits like comprehensive health insurance, 401(k) matching, and flexible work arrangements, among other benefits.