AI/ML Software Engineer III — TPU Efficiency (Equity + Bonus)

Google; Mountain View (CA); On-site; USD 147,000 - 210,000; Full time

Job summary

Google is seeking a software engineer to optimize YouTube's ML models and infrastructure. You will tackle model efficiency, quantization, distillation, and hardware-friendly architectures, working across the YouTube recommendation stack on TPU-enabled systems.

You will collaborate with researchers and engineers to deploy scalable, energy-efficient ML solutions that reduce training and serving costs while enhancing user experience at scale.

Qualifications

• Bachelor's degree or equivalent practical experience.
• 2 years of experience with ML infrastructure (deployment, evaluation, data processing, debugging).
• 2 years of experience with accelerator hardware architectures (TPUs/GPUs).
• 2 years of experience programming in C++ and Python.
• Experience with ML frameworks such as TensorFlow, JAX, and PyTorch, or ML compilers (e.g., XLA).
• Experience with ML model optimization.

Responsibilities

• Analyze ML workloads, optimize accelerator utilization to maximize compute efficiency.
• Develop and productionize efficiency techniques (low-precision quantization, distillation, sharing).
• Collaborate with model developers to deploy hardware-friendly architectures.

Skills

ML infrastructure

Accelerator hardware

C++ & Python

ML frameworks (TensorFlow, JAX, PyTorh

ML model optimization

Education

Bachelor's degree or equivalent practical experience

Job description

Google is seeking a software engineer to optimize YouTube's ML models and infrastructure. You will tackle model efficiency, quantization, distillation, and hardware-friendly architectures, working across the YouTube recommendation stack on TPU-enabled systems.

You will collaborate with researchers and engineers to deploy scalable, energy-efficient ML solutions that reduce training and serving costs while enhancing user experience at scale.