Applied AI Engineer — Multi-Agent & Go-Live Infra

Google; Greater London; On-site; GBP 120,000 - 180,000; Full time

Job summary

Google Cloud seeks an experienced AI/GenAI engineer to design and deploy agentic systems that scale for enterprise customers. You will build evaluation pipelines, optimize CUJs, and ensure production readiness across complex workflows.

The role emphasizes handling multilingual NLP models, calibrating tool selection, and maintaining security and performance during Go-Live windows. Travel up to 50% is possible.

Qualifications

• Bachelor's degree or equivalent practical experience.
• 6+ years of software development with Python or similar languages.
• Experience designing AI systems on cloud platforms (GCP).
• Experience developing AI/GenAI solutions utilizing AI tools, or designing multi-agent workflows or RAG systems.
• Experience developing and deploying multilingual NLP models.

Responsibilities

• Build high-performance evaluation pipelines and observability for agentic systems to ensure accuracy, safety, and latency.
• Own the delivery of Customer User Journeys (CUJs), ensuring conversational flows are production-ready for top priorities.
• Architect and optimize complex agent workloads, focusing on reasoning loops, tool selection, and reducing latency with secure networking.
• Implement critical infrastructure including rate limiting, error handling, and regional failover; develop monitoring and alerting for Go-Live windows.

Skills

Python

AI systems on cloud

GenAI solutions

Multilingual NLP models

Education

Bachelor's degree or equivalent

Tools

GCP

RAG workflows

Agent reasoning loops

Job description

Google Cloud seeks an experienced AI/GenAI engineer to design and deploy agentic systems that scale for enterprise customers. You will build evaluation pipelines, optimize CUJs, and ensure production readiness across complex workflows.

The role emphasizes handling multilingual NLP models, calibrating tool selection, and maintaining security and performance during Go-Live windows. Travel up to 50% is possible.