Software Engineer, Model Inference

Google; Greater London; On-site; GBP 160,000 - 200,000; Full time

Benefits offered by this job

Learning opportunities

Career growth

Job summary

Google DeepMind is seeking a senior ML systems engineer to deploy and optimize large language models on Google's production infrastructure. You will work closely with research teams to design high-performance model serving solutions and drive efficiency across hardware accelerators.

The role focuses on profiling, tuning, and deploying models at scale with opportunities for IC and technical lead growth. London or Mountain View locations supported.

Qualifications

• Bachelor’s degree or equivalent practical experience.
• 8 years of software development experience.
• 2 years deploying and maintaining ML models in production.
• Experience profiling ML workloads on GPUs or TPUs.
• Experience designing/optimizing model serving infrastructure.

Responsibilities

• Collaborate with research teams to understand production-friendly modeling approaches.
• Work with infrastructure teams to deliver efficient, high-performance serving infrastructure.
• Identify opportunities to automate tasks, remove redundancies, and improve ML release velocity.
• Gain deep understanding of serving frameworks, pre-processing pipelines, and caching mechanisms.
• Use roofline analysis and hardware profiling to address bottlenecks across ML stacks.

Skills

Software development

ML model deployment

Profiling on GPUs/TPUs

Model serving infrastructure

Collaboration with researchers

Education

Bachelor’s degree or equivalent practical experience

Tools

CUDA

PyTorch

Model serving frameworks

Job description

Salary: £160,000 - 200,000 per year

Requirements:

• We require a bachelors degree or equivalent practical experience.
• We require 8 years of experience in software development.
• We require 2 years of experience deploying and maintaining machine learning models in a live production environment.
• We require experience profiling, configuring, or executing ML workloads directly on hardware accelerators such as GPUs or TPUs.
• We require experience designing, building, or optimizing model serving infrastructure or inference backends.

Responsibilities:

• We collaborate closely with research teams to understand next-generation modeling approaches and ensure they are designed and implemented with production considerations in mind.
• We work with infrastructure teams to deliver serving infrastructure that is designed for maximum efficiency and performance, addressing bottlenecks in speed, scale, and quality.
• We identify opportunities to automate tasks, eliminate redundancies, build performant tests, and improve the overall velocity of model releases.
• We gain a deep understanding of serving frameworks, pre-processing pipelines, caching mechanisms, and other relevant technologies.
• We leverage roofline analysis, hardware-level profiling, and systems analysis to identify and eliminate performance bottlenecks across ML frameworks, compilers, custom kernels, and serving infrastructure on hardware accelerators.

Technologies:

• AI
• Hardware
• Machine Learning
• Model Serving
• 3D
• AI Agents
• CUDA
• LLM
• PyTorch

More:

At Google DeepMind, we are building the worlds first general-purpose learning agent and advancing AI to solve complex global challenges and accelerate high-quality product innovation for billions of users. We work across multiple teams and offer opportunities for both individual contributor and technical lead growth, with openings for Software Engineering and Research Engineering backgrounds. This role involves bringing AI research to life by working directly with researchers and engineers to optimize and deploy large language models such as Gemini onto Googles production infrastructure. We offer learning opportunities, varied career pathways, and benefits at Google, and the position is open to preferred working locations in London, UK or Mountain View, CA, USA.

last updated 36 week of 2026