Staff AI Engines Engineer: TPU Inference & ML Runtime

Socket.dev; Mountain View (CA); On-site; USD 207,000 - 300,000; Full time

Job summary

Google is seeking a Staff Software Engineer to advance ML infrastructure, runtimes, and compiler tech at scale in Mountain View. You will guide engineering choices, lead cross-team initiatives, and drive deployment of multi-framework runtimes within Google Cloud and partner products.

This role emphasizes leadership in ML design, collaboration with Research, and delivering high-performance ML software infrastructure across large-scale systems.

Qualifications

• Bachelor’s degree or equivalent practical experience.
• 8 years of experience in software development.
• 5 years testing, launching software products, and 3 years in software design/architecture.
• 5 years with one or more: speech/audio, reinforcement learning, ML infrastructure, or related ML field.
• 5 years with ML design and ML infrastructure (model deployment, evaluation, data processing, debugging, fine tuning).

Responsibilities

• Exercise judgment to guide sustainable engineering choices for ML systems at scale.
• Innovate directions for infrastructure over a 12-month horizon amid rapid tech changes.
• Deliver impactful capability and optimization for Cloud and partner products.
• Migrate TensorFlow, JAX, PyTorch runtimes and workflows onto ML Runtime with minimal user disruption.
• Partner with GDM to transfer key innovations into products across teams.

Skills

Software development experience

Software testing

Software launches

Software design & architecture

ML design & infrastructure

ML systems & runtimes

Leadership in tech

Cross-functional collaboration

TPU/GPU experience

ML compilers & runtimes

Education

Bachelor’s degree or equivalent practical experience

Master’s degree or PhD preferred

Tools

TensorFlow

JAX

PyTorch

Job description

Google is seeking a Staff Software Engineer to advance ML infrastructure, runtimes, and compiler tech at scale in Mountain View. You will guide engineering choices, lead cross-team initiatives, and drive deployment of multi-framework runtimes within Google Cloud and partner products.

This role emphasizes leadership in ML design, collaboration with Research, and delivering high-performance ML software infrastructure across large-scale systems.