Build production-ready LLM agent systems at Infoya as a hands-on AI Platform Engineer in Toronto, working hybrid two days weekly in office. Apply Google ADK, Kubernetes, and practical AI governance across enterprise solutions.

This permanent position owns AI solutions from architecture through deployment and monitoring. You will design agent systems, build MCP servers, integrate REST APIs, and address production concerns including retries, oversized responses, tool timeouts, and token costs. The work also includes forecasting and anomaly detection using production metrics.

Key Responsibilities:

- Design and operate LLM agent systems using Google ADK or comparable frameworks
- Deliver architectures through coding, CI/CD, Kubernetes, deployment, and monitoring
- Build MCP server tools and integrate REST APIs




- Develop forecasting and anomaly detection from production metrics
- Apply safeguards, evaluations, audit logging, and cost limits

Requirements:

- Bachelor’s degree or equivalent experience in a related field
- 4+ years shipping LLM agent systems into production
- Experience with CI/CD, Kubernetes or cloud, and post-launch monitoring
- Experience integrating MCP servers with REST APIs
- Experience managing production AI safety and operational trade-offs

Bring LLM engineering, production operations, anomaly detection, and AI governance expertise to Infoya’s Toronto platform team.

📌 LLM Agent Systems Engineer (Toronto)
🏢 Infoya
📍 Toronto