Remote opportunity at
Grafana LabsStaff AI Engineer | US | Remote
Role overview. Grafana Labs is recruiting a Staff AI Engineer, titled in the posting as a Staff Engineer for AI and Automation. The full-time role is…
Career Tools
About This Role
Role overview. Grafana Labs is recruiting a Staff AI Engineer, titled in the posting as a Staff Engineer for AI and Automation. The full-time role is remote and open to candidates in the United States. The engineer owns the infrastructure for AI agents and the automation platform behind the company's Marketing Operations organization. Scope. The engineer designs multi-agent systems, LLM connectors and backend services that link AI models with company…
Job Description
Role overview. Grafana Labs is recruiting a Staff AI Engineer, titled in the posting as a Staff Engineer for AI and Automation. The full-time role is remote and open to candidates in the United States. The engineer owns the infrastructure for AI agents and the automation platform behind the company's Marketing Operations organization.
Scope. The engineer designs multi-agent systems, LLM connectors and backend services that link AI models with company systems and outside data sources. Beyond building, the role steers the automation platform technically, covering schemas, endpoint contracts, shared code libraries and reference designs. Teammates in the data engineering group, the GTM systems team and field operations help shape the work, alongside revenue operations, campaign staff, regional marketers and the SDR group, with the aim of turning manual steps into self-service tools. The posting asks the engineer to diagnose business problems before writing any code.
Technical emphasis. Expected work includes MCP servers, APIs, command-line tools and microservices that link models to systems such as BigQuery, Slack, CRMs, email and calendars, along with retrieval-augmented generation pipelines and serverless or containerized services on Google Cloud. Governance is part of the brief: access controls, audit trails, handling of personal data and human escalation paths for AI workflows.
Who it suits. The posting requires eight or more years of software engineering experience, including two or more years applying LLMs to production workflows. Strong Python and JavaScript or Node.js skills, experience with Google Cloud and BigQuery, and hands-on work running multi-agent systems is expected. Candidates should understand common LLM failure modes and how to handle them with fallbacks, confidence thresholds and human review.
Responsibilities
- Own the design, build, testing, deployment and operation of multi-agent AI systems
- Build reusable agent skills that can be invoked from Slack, dashboards, internal apps and CLIs
- Build MCP servers, APIs, command-line tools and microservices that link AI models to business systems
- Architect retrieval-augmented generation data flows that connect LLMs to knowledge bases and business context
- Implement observability, evaluation, cost management and governance for AI workflows
- Design and deploy workflows that follow continuous delivery practice, with testing and production-grade reliability
- Scope automation problems with partner teams and build self-service tools with documentation
Requirements
- Eight or more years building software, with depth in backend work, systems integration or data engineering
- Two or more years of hands-on experience applying LLMs and AI to production workflows
- Strong Python and JavaScript or Node.js skills, with Git-based workflows and testing discipline
- Experience with prompt engineering, RAG, function calling, structured output and model evaluation
- Experience running multi-agent systems in production, including orchestration patterns and state handling
- Working knowledge of Google Cloud Platform, BigQuery, Cloud Functions and Cloud Run
- Awareness of how LLMs fail, plus mitigations such as confidence thresholds, fallbacks and human escalation
- Clear communication with both engineers and business stakeholders
Qualifications
- Experience with vector stores or retrieval pipelines
- Exposure to marketing or sales systems like Salesforce, HubSpot or Marketo
- Experience with React or Slack Block Kit for AI tool interfaces
- Experience with AI observability tools or workflow platforms such as n8n, Temporal, Prefect or Airflow
- Familiarity with the Model Context Protocol
- Earlier projects that automated go-to-market or customer success processes at a B2B SaaS firm
Core Skills
Benefits
- Restricted Stock Units (RSUs)
Frequently Asked Questions
Answers are based only on the employer’s listing; where it doesn’t say, neither do we.
Is this role remote?
Yes. The posting is remote and considers candidates from the United States.
What experience is required?
The posting asks for eight or more years of software engineering experience and two or more years applying LLMs to production workflows.
What is the pay range?
The posting gives a U.S. base compensation range of USD $154,445 to $185,334. It says actual pay depends on level, experience and skill set.
How do I apply?
The posting does not describe the application steps.
Sample Interview Questions
AI-generated questions tailored to this specific role — a preview of the full practice set.
