About the Job:

We're looking for a hands-on AI Platform Engineer to build and operate production-ready LLM agent systems and anomaly detection tools. You'll own solutions from design through deployment and monitoring, apply practical AI governance, and identify opportunities to improve how engineering and operations teams work.

Office Location:

Toronto

Employment Type:

Permanent

Work Arrangement:

Hybrid (2 days in office)

Position Responsibilities:

- Design, build, and operate LLM agent systems using Google ADK or a comparable framework such as LangGraph, CrewAI, AutoGen, or OpenAI Agents SDK.
- Own delivery end to end, including architecture, coding, containerization, CI/CD, deployment to Kubernetes or cloud infrastructure, and post-launch monitoring.
- Build agent tools as MCP servers and integrate with REST APIs.
- Address production concerns such as tool timeouts, oversized responses, retries, and token costs.
- Develop or improve time-series forecasting and anomaly detection using production metrics, such as Prometheus or Grafana data.
- Tune detection thresholds against real incidents and balance false positives against missed alerts.
- Use AI coding tools such as Claude Code, Cursor, or Copilot regularly as part of daily engineering work.
- Extend AI coding tools for team use through plugins, skills, slash commands, hooks, or MCP integrations.
- Review and verify AI-generated code before it ships.
- Apply safeguards to AI systems, including code-enforced access controls, PII and secrets handling, audit logging, cost limits, and model output evaluation.
- Work with security and compliance teams through internal review processes.




- Identify opportunities by observing how engineering and operations teams work, then prototype and deliver tools that people adopt.

About the Job:

We're looking for a hands-on AI Platform Engineer to build and operate production-ready LLM agent systems and anomaly detection tools. You'll own solutions from design through deployment and monitoring, apply practical AI governance, and identify opportunities to improve how engineering and operations teams work.

Office Location:

Toronto

Employment Type:

Permanent

Role Type:

Current position - current requirement

Work Arrangement:

Hybrid (2 days in office)

Position Responsibilities:

- Design, build, and operate LLM agent systems using Google ADK or a comparable framework such as LangGraph, CrewAI, AutoGen, or OpenAI Agents SDK.
- Own delivery end to end, including architecture, coding, containerization, CI/CD, deployment to Kubernetes or cloud infrastructure, and post-launch monitoring.
- Build agent tools as MCP servers and integrate with REST APIs.
- Address production concerns such as tool timeouts, oversized responses, retries, and token costs.
- Develop or improve time-series forecasting and anomaly detection using production metrics, such as Prometheus or Grafana data.




- Tune detection thresholds against real incidents and balance false positives against missed alerts.
- Use AI coding tools such as Claude Code, Cursor, or Copilot regularly as part of daily engineering work.
- Extend AI coding tools for team use through plugins, skills, slash commands, hooks, or MCP integrations.
- Review and verify AI-generated code before it ships.
- Apply safeguards to AI systems, including code-enforced access controls, PII and secrets handling, audit logging, cost limits, and model output evaluation.
- Work with security and compliance teams through internal review processes.
- Identify opportunities by observing how engineering and operations teams work, then prototype and deliver tools that people adopt.

Requirements

Required Qualifications:

- Bachelor's degree in Computer Science, Engineering, or related field (or equivalent experience).
- 4+ years of experience shipping LLM agent system to production within a company.
- End-to-end experience with a production agent system, including architecture, implementation, deployment through CI/CD to Kubernetes or cloud, and monitoring after launch.
- Experience building agent tools as MCP servers and integrating with REST APIs.
- Understanding of production issues such as tool timeouts, oversized responses, retries, and token cost management.
- Hands-on experience with time-series forecasting or anomaly detection on real production metrics.
- Experience tuning alert thresholds against real incidents and managing the trade-off between false positives and missed alerts.
- Regular use of AI coding tools as part of daily engineering work, with a disciplined approac

📌 AI Platform Engineer (Toronto)
🏢 Infoya
📍 Toronto