AI Platform Engineer - GCP, LLM Ops & Security

Kaizen Global Technologies; Sydney; On-site; AUD 120,000 - 180,000; Full time

Job summary

Kaizen Global Technologies in Sydney seeks a hands-on Platform Operations Engineer to own the operational lifecycle of AI agents, including LLM evaluations, version upgrades, and platform security.

You will manage and maintain GCP infrastructure (Agent Runtime, Cloud Run, Cloud SQL, Load Balancers), implement robust monitoring and observability, and ensure authentication controls with Okta, collaborating across teams to uphold governance and reliability.

Qualifications

• Strong hands-on experience with GCP services, particularly Cloud Run, Cloud SQL, Load Balancing, and Agent Runtime.
• Experience with AI/ML platform operations, including LLM evaluation, AI agent lifecycle management, and Agent Runtime orchestration.
• Proficiency in monitoring, observability, and metric analysis using cloud and AI-platform monitoring tools such as Braintrust.
• Experience with Identity & Access Management (IAM) and authentication solutions, particularly Okta.
• Strong understanding of cloud security, infrastructure operations, governance, troubleshooting, and cross-functional collaboration.

Responsibilities

• Manage the operational lifecycle of AI agents, including LLM evaluations, version upgrades, and platform security.
• Manage and maintain GCP infrastructure including Agent Runtime, Cloud Run, Cloud SQL, and Load Balancers.
• Implement monitoring and observability solutions to track platform metrics, identify issues, and improve performance.
• Configure and maintain authentication and access controls, including Okta integration and secure infrastructure practices.
• Collaborate with cross-functional teams to manage shared services, core infrastructure, governance, and operational standards.

Skills

AI platform operations

Cross-functional collaboration

Monitoring & observability

Security mindset

Tools

GCP Cloud Run

GCP Cloud SQL

Load Balancers

Agent Runtime orchestration

Okta IAM

Braintrust monitoring tools

Job description

Kaizen Global Technologies in Sydney seeks a hands-on Platform Operations Engineer to own the operational lifecycle of AI agents, including LLM evaluations, version upgrades, and platform security.

You will manage and maintain GCP infrastructure (Agent Runtime, Cloud Run, Cloud SQL, Load Balancers), implement robust monitoring and observability, and ensure authentication controls with Okta, collaborating across teams to uphold governance and reliability.