Staff AI Engineer - Grafana Labs

The Opportunity

Grafana Labs is seeking a Staff Engineer (AI & Automation) to own the AI agent infrastructure and automation platform that powers our Marketing Operations organization. You will build multi-agent architectures, LLM integrations, and backend services that connect AI models to internal and third-party data platforms.

This is a high-autonomy role where you will define the technical direction for the automation platform, including data models, API contracts, and shared libraries, while partnering with Data Engineering and GTM Systems to build scalable, self-service automation.

What You'll Be Doing

Agentic Systems & AI Infrastructure

• Own end-to-end development of multi-agent AI systems, from architecture through deployment and operation.
• Build modular, composable agentic systems using orchestration frameworks (e.g., LangChain, CrewAI, Anthropic MCP).
• Develop reusable agentic skills for interfaces like Slack, dashboards, and CLIs.
• Implement observability, performance metrics, prompt iteration, and cost management.
• Establish governance, compliance, and PII handling standards for AI workflows.

Systems Integration & Backend Services

• Build MCP servers, APIs, and microservices connecting AI models to business systems (BigQuery, Slack, CRMs, etc.).
• Architect data flows for RAG, connecting LLMs to internal knowledge bases and real-time business context.
• Build serverless or containerized services (GCP Cloud Functions, Cloud Run) that scale with usage.

Automation & Workflow Enablement

• Partner with RevOps, Demand Gen, and SDR teams to identify bottlenecks and build high-impact automation.
• Design workflows using orchestration tools (n8n, Workato) with CI/CD and production reliability standards.
• Create documentation and playbooks to enable partner teams to operate independently.

What Makes You a Great Fit

• 8+ years of software engineering experience with depth in backend, systems integration, or data engineering.
• 2+ years of hands-on experience applying LLMs/AI to production workflows.
• Strong proficiency in Python and JavaScript/Node.js.
• Experience with LLM frameworks, RAG, function calling, and structured output parsing.
• Expertise in building multi-agent systems (orchestration, state management, monitoring).
• Deep familiarity with Google Cloud Platform, BigQuery, and serverless/containerized services.
• Ability to diagnose business problems and think in terms of workflows and outcomes.
• Fluent with AI-assisted development tools (GitHub Copilot, Cursor, Claude Code).

Why You’ll Thrive at Grafana Labs

• 100% Remote: A global, collaborative culture.
• Innovation-Driven: High autonomy and support to ship great work.
• Open Source Roots: Built on community-driven values.
• Balance: 30 days annual leave, including company-wide shutdown days.
• Ownership: All roles include Restricted Stock Units (RSUs).