Tech Lead Manager, TPU Inference at Scale

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

In most instances, this position requires in-person interviews as part of the hiring process.

Minimum qualifications

• Bachelor’s degree or equivalent practical experience.
• 8 years of experience in software development.
• 5 years of experience with one or more of the following: Speech/audio (e.g., technology duplicating and responding to the human voice), reinforcement learning (e.g., sequential decision making), ML infrastructure, or specialization in another ML field.
• 5 years of experience leading ML design and optimizing ML infrastructure (e.g., model deployment, model evaluation, data processing, debugging, fine tuning).
• 3 years of experience in a technical leadership role.
• 2 years of experience in a people management or team leadership role.

Preferred qualifications

• Master’s degree or PhD in Engineering, Computer Science, or a related technical field.
• 3 years of experience working in a complex, matrixed organization involving cross-functional, or cross-business projects.

About The Job

Like Google's own ambitions, the work of a Software Engineer goes beyond just Search. Software Engineering Managers have not only the technical expertise to take on and provide technical leadership to major projects, but also manage a team of Engineers. You not only optimize your own code but make sure Engineers are able to optimize theirs. As a Software Engineering Manager you manage your project goals, contribute to product strategy and help develop your team. Teams work all across the company, in areas such as information retrieval, artificial intelligence, natural language processing, distributed computing, large-scale system design, networking, security, data compression, user interface design; the list goes on and is growing every day. Operating with scale and speed, our exceptional software engineers are just getting started -- and as a manager, you guide the way.

With technical and leadership expertise, you manage engineers across multiple teams and locations, a large product budget and oversee the deployment of large-scale projects across multiple sites internationally.

As a Tech Lead Manager, you will use your knowledge in LLM or diffusion model internals for large-scale workloads. You will use your expertise in optimization techniques designed for LLM models and TPU or GPU Kernels.

Google Cloud accelerates every organization’s ability to digitally transform its business and industry. We deliver enterprise-grade solutions that leverage Google’s cutting‑edge technology, and tools that help developers build more sustainably. Customers in more than 200 countries and territories turn to Google Cloud as their trusted partner to enable growth and solve their most critical business problems.

Individual pay is determined by factors including job‑related skills, experience, and relevant education or training.

US: $207000 - $300000 (USD) + 20% bonus target + equity + benefits

Responsibilities

Learn more about benefits at Google .

• Work with LLM/Non‑LLM models bringup to performance tuning/optimization on Google Cloud TPUs. Manage up to 6 engineers to drive and deliver results as a TLM.
• Manage onboarding emerging open‑weights models models in industry.
• Drive performance optimization for massive‑scale models by engineering advanced sharding strategies (2D/3D parallelism), developing custom Pallas kernels, and maximizing utilization across single‑host and multi‑host TPU.
• Design and implement key features such as TorchTPU support, disaggregated serving, RL inference, etc.
• Collaborate with the ML research, ML performance, model optimization tooling, and other optimization teams. Participate in ML Perf Inference submissions.

Google is proud to be an equal opportunity workplace and is an affirmative action employer. We are committed to equal employment opportunity regardless of race, color, ancestry, religion, sex, national origin, sexual orientation, age, citizenship, marital status, disability, gender identity or Veteran status. We also consider qualified applicants regardless of criminal histories, consistent with legal requirements. See also Google's EEO Policy and EEO is the Law. If you have a disability or special need that requires accommodation, please let us know by completing our Accommodations for Applicants form .