Senior AI Engineer | Canada | Remote

Grafana Labs is hiring a remote Senior AI Engineer in Canada to build and own the AI agent infrastructure that powers our Marketing Operations organization. If you turn LLMs into dependable production systems, this is a career-defining opportunity to shape technical direction end to end.

About the Role

As a Senior Engineer (AI & Automation), you will design multi-agent architectures, LLM integrations, and backend services that link AI models to internal and third-party data platforms. This is a high-autonomy position: you will surface the highest-leverage problems across Marketing, RevOps, and SDR teams, architect the solutions, and ship production systems that colleagues rely on every day. You'll set the technical direction for the automation platform — data models, API contracts, shared libraries, and reference architectures — collaborating with Data Engineering, GTM Systems, and Field Operations to deliver scalable, self-service automation.

Key Responsibilities

• Own multi-agent AI systems from architecture and build through testing, deployment, and 24/7 operation using frameworks such as LangChain, CrewAI, or Anthropic MCP.
• Create reusable agentic skills invoked across Slack, dashboards, internal apps, and CLIs.
• Add observability and feedback loops — logging, performance metrics, prompt iteration, model evaluation, and cost control.
• Define governance for AI workflows: access controls, audit trails, PII handling, and human-in-the-loop escalation.
• Build MCP servers, APIs, CLIs, and microservices connecting LLMs to BigQuery, Slack, CRMs, email, calendars, and analytics tools, including RAG data flows.
• Deploy serverless and containerized services on GCP Cloud Functions and Cloud Run, plus workflows via n8n, Workato, or custom platforms with CI/CD and production reliability.

Qualifications

• 8+ years in software engineering with depth in backend, systems integration, or data/analytics engineering.
• 2+ years applying LLMs to real production workflows, not prototypes.
• Strong Python and JavaScript/Node.js skills with disciplined Git workflows, code review, and testing.
• Hands-on experience with prompt engineering, RAG, function calling, structured output, and evaluation.
• Experience operating multi-agent systems at scale, including orchestration patterns and production monitoring.
• Deep familiarity with Google Cloud Platform, BigQuery, and serverless/containerized services.
• Fluency with AI-assisted development tools such as GitHub Copilot, Cursor, and Claude Code.

About Grafana Labs

Grafana Labs is the company behind the open observability cloud, trusted by 35M+ users and 7,000+ customers including Anthropic, NVIDIA, and Microsoft. We are a 100% remote organization of 1,600+ team members across 40+ countries, rooted in open source, transparency, and autonomy.

How to Apply

To apply, complete your application directly on this page, or you'll be redirected to the employer's application platform to finish submitting there.