Model Inference Engineer: ML Serving & Hardware

Google Inc.; Mountain View (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Google DeepMind seeks a Software Engineer to advance model inference and deployment for cutting-edge AI agents. You will work with researchers and engineers to optimize large language models and serving backends, while improving performance on production infrastructure and hardware accelerators.

The role spans IC and TL paths across multiple teams. The ideal candidate has deep software engineering and ML deployment experience, with a focus on efficiency, reliability, and scalable systems for a

Qualifications

• 8 years of experience in software development.
• Experience deploying and maintaining ML models in production.
• Experience with hardware accelerators (GPU/TPU).
• Experience designing or optimizing model serving infra.
• Strong software engineering foundations.

Responsibilities

• Collaborate with Research teams on next generation modeling with production considerations.
• Deliver serving infrastructure for speed, scale, and quality.
• Automate tasks, reduce redundancies, and improve model release velocity.
• Deeply understand serving frameworks, pre-processing pipelines, caching, and related tech.
• Use profiling and systems analysis to remove bottlenecks across ML frameworks and kernels.

Skills

Software dev

ML deployment

Hardware accel

Model serving

Profiling

Education

Bachelor's degree or equivalent practical experience

Job description

Google DeepMind seeks a Software Engineer to advance model inference and deployment for cutting-edge AI agents. You will work with researchers and engineers to optimize large language models and serving backends, while improving performance on production infrastructure and hardware accelerators.

The role spans IC and TL paths across multiple teams. The ideal candidate has deep software engineering and ML deployment experience, with a focus on efficiency, reliability, and scalable systems for a