Tech Lead Manager — LLM & AI Systems

Google; Sunnyvale (CA); On-site; USD 207,000 - 300,000; Full time

Job summary

Google is seeking a Software Engineering Manager with deep expertise in ML and large-scale systems. You will lead teams across ML design, deployment, and performance optimization on Google Cloud TPUs, guiding architecture and strategy while developing and mentoring engineers.

You will oversee multi-team projects, contribute to product direction, and manage a budget for large-scale deployments across sites. Strong leadership and advanced ML knowledge are essential.

Qualifications

• 8 years of software development experience.
• 5 years of experience with ML, speech/audio, RL, ML infrastructure or related field.
• 5 years of experience leading ML design and optimizing ML infrastructure.
• 3 years in a technical leadership role.
• 2 years in people management or team leadership.

Responsibilities

• Lead ML model bring-up and performance tuning on Google Cloud TPUs with up to 6 engineers.
• Oversee onboarding of emerging open-weight models in the industry.
• Drive performance optimization for massive-scale models via advanced sharding and custom kernels.
• Design and implement features such as TorchTPU support and disaggregated serving.
• Collaborate with ML research, performance, tooling teams and contribute to MLPerf Inference.

Skills

Software development experience

ML design and infrastructure

Technical leadership

People management

ML optimization

Education

Bachelor's degree or equivalent practical experience

Master's degree or PhD in Engineering/CS

Job description

Google is seeking a Software Engineering Manager with deep expertise in ML and large-scale systems. You will lead teams across ML design, deployment, and performance optimization on Google Cloud TPUs, guiding architecture and strategy while developing and mentoring engineers.

You will oversee multi-team projects, contribute to product direction, and manage a budget for large-scale deployments across sites. Strong leadership and advanced ML knowledge are essential.