Build production-ready LLM agent systems and anomaly detection tools as an AI Platform Engineer in Toronto’s hybrid workplace.
This permanent position covers design, coding, deployment, monitoring, and practical AI governance. You will work with Google ADK or comparable frameworks, MCP servers, REST APIs, Kubernetes or cloud infrastructure, and production metrics.
Key Responsibilities: Design, build, and operate production LLM agent systems
Own architecture, coding, containerization, CI/CD, deployment, and monitoring
Build MCP server tools and integrate REST APIs
Address timeouts, oversized responses, retries, and token costs
Apply safeguards and support security and compliance reviews
Requirements: Bachelor’s degree or equivalent experience in a related field
Four or more years shipping LLM agent systems
Production experience deploying agents through CI/CD to Kubernetes or cloud
Experience with MCP servers, REST APIs, and production concerns
Experience with enterprise AI safeguards and model evaluation
Bring hands-on platform engineering, LLM agents, deployment, monitoring, and governance experience to this Toronto-based hybrid role.