Senior AI Engineer

About this role

Build and ship AI-powered observability features that help users detect, triage, and resolve incidents. The role focuses on practical LLM and agent workflows, rapid experimentation with users, and production-ready solutions for incident response.

About the company

Grafana Labs builds open-source and commercial observability tools for metrics, logs, and traces, centered on Grafana dashboards. It helps teams monitor infrastructure and applications and investigate incidents.

The team

Grafana AI teams

Stack

What you'll do

• Develop high-performance AI features for incident detection, triage, and resolution.
• Prototype, test, and iterate on LLM- and agent-powered workflows with user feedback.
• Integrate agentic components with internal tools, alerting systems, runbooks, and developer workflows.
• Own AI solutions through delivery, ensuring they are scalable, maintainable, and aligned with user workflows.
• Collaborate with analysts, product managers, designers, and engineering peers.

What we're looking for

• Experience with LLMs, prompt engineering, and GenAI applications.
• Track record of delivering production software actively used by users.
• Experience building production software systems, with strong backend and/or full-stack engineering skills.
• Exposure to cloud-native environments such as AWS, GCP, or Azure.
• Experience using observability tools to troubleshoot system behavior.
• Strong communication, ownership, and ability to work through ambiguity.

Nice to have

• Experience with agent frameworks or multi-agent workflows.
• Familiarity with Kubernetes, Docker, Terraform, or similar infrastructure tools.
• Familiarity with model fine-tuning.
• Experience building observability tooling.

Benefits

• Restricted Stock Units (RSUs)
• 30 days of annual leave, including three Grafana Shutdown Days
• Company-funded budget for AI coding assistants
• In-person onboarding