ML Systems Engineer: LLM Deployment & Performance

DeepMind Technologies Limited; Madison (WI); On-site; USD 207,000 - 300,000; Full time

Job summary

Google DeepMind is seeking a Software Engineer to help deploy and optimize large language models and AI agents on our production infrastructure. You will work with researchers and engineers to build efficient serving, testing, and validation pipelines, and contribute to performance tuning across hardware accelerators.

You will have opportunities across IC and TL tracks, with roles spanning software and research engineering, and you will contribute to a high-impact, mission-driven team focused on

Qualifications

• Bachelor’s degree or equivalent practical experience.
• 8 years of experience in software development.
• 2 years of experience deploying and maintaining ML models in production.
• Experience profiling, configuring, or executing ML workloads on hardware accelerators (GPU/TPU).
• Experience designing, building, or optimizing model serving infrastructure.

Responsibilities

• Collaborate with Research teams to understand next generation modeling approaches with production considerations.
• Work with infrastructure teams to deliver serving infrastructure for speed, scale and quality.
• Identify opportunities to automate tasks, reduce redundancies, and improve model release velocity.
• Gain understanding of serving frameworks, pre-processing pipelines, caching, and related tech.
• Use roofline analysis and profiling to find and fix performance bottlenecks across ML frameworks, compilers (XLA), kernels (Pallas), and serving infra on TPUs/GPUs.

Skills

Software development

ML model deployment

ML workloads profiling

Model serving infrastructure

Hardware accelerators (GPUs/TPUs)

Education

Bachelor’s degree or equivalent practical experience

Tools

GPUs

TPUs

Job description

Google DeepMind is seeking a Software Engineer to help deploy and optimize large language models and AI agents on our production infrastructure. You will work with researchers and engineers to build efficient serving, testing, and validation pipelines, and contribute to performance tuning across hardware accelerators.

You will have opportunities across IC and TL tracks, with roles spanning software and research engineering, and you will contribute to a high-impact, mission-driven team focused on