- Agent Platform Operations: Lead the operational lifecycle of AI agents, including conducting rigorous LLM evaluations, managing version upgrades, and enforcing robust platform security protocols.
- GCP Infrastructure Management: Oversee and maintain the platform's cloud infrastructure, including Agent Runtime, Cloud Run, Cloud SQL, and Load Balancers to ensure seamless operation.
- Monitoring & Insights: Implement and manage advanced monitoring solutions (e.g., Cloud, Braintrust) to track platform-specific metrics, enabling proactive issue resolution and continuous performance tuning.
- Identity & Access Management: Configure and maintain authentication services, including Okta integration, to ensure secure access across the platform.
- Shared Services & Governance:
Collaborate with cross-functional teams to manage shared services and core infrastructure components, ensuring alignment with project standards and operational governance.