Senior AI Inference Platform Architect

Google; Sunnyvale (CA); On-site; USD 262,000 - 365,000; Full time

Benefits offered by this job

Bonus target 25%

Equity

Benefits

Job summary

Google Cloud in Sunnyvale, CA is seeking a Senior Staff Software Engineer to architect and lead the core infrastructure powering our most advanced LLMs and Agentic AI capabilities. You will own the global platform strategy across LLM serving, multi‑agent orchestration, and secure, high‑performance execution.

You will define the technical vision, partner with AI Research, SRE, and product teams, and drive production‑ready AI solutions for enterprise customers.

Qualifications

• Bachelor's degree or equivalent practical experience.
• 8 years of experience with software development in C++, Java, Python, Kotlin, or Go.
• 5 years of experience testing, and launching software products.
• 4 years of experience in technical leadership leading architecture and delivery of large-scale distributed systems.
• 3 years of experience with software design and architecture.

Responsibilities

• Define the GDC AI infrastructure roadmap for LLM serving and Agentic AI platforms.
• Architect scalable LLM serving infrastructure with optimizations for resource efficiency.
• Build core platforms for multi-agent systems, tool integration, state persistence, and isolation.
• Collaborate with AI Research, SRE, Product, and core platform teams on AI solutions.
• Resolve high-impact systems issues balancing enterprise needs with architecture.

Skills

C++

Java

Python

Kotlin

Go

Distributed systems

Cloud infrastructure

Technical leadership

Arch design

Education

Bachelor's degree

Master’s degree or PhD

Tools

Kubernetes

Docker

Job description

Google Cloud in Sunnyvale, CA is seeking a Senior Staff Software Engineer to architect and lead the core infrastructure powering our most advanced LLMs and Agentic AI capabilities. You will own the global platform strategy across LLM serving, multi‑agent orchestration, and secure, high‑performance execution.

You will define the technical vision, partner with AI Research, SRE, and product teams, and drive production‑ready AI solutions for enterprise customers.