Grafana Labs is a remote-first, open-source powerhouse seeking a Staff GTM Engineer (AI & Automation) to build next-generation AI agent and workflow systems. The role involves designing multi-agent architectures, integrating LLM APIs, and delivering automation that enhances marketing and operational workflows across teams.
Responsibilities:
- Build & operate GTM automation systems
- Implement modular, scalable, multi-agent AI systems that operate 24/7 and integrate with marketing platforms (e.g., Customer.io, Marketo, Salesforce, BigQuery)
- Own technical direction for GTM automation: design data models, define API contracts, build shared libraries, and maintain reference architectures used across teams
- Review code, write tests, and maintain production reliability standards
- Partner with RevOps, Demand Generation, Regional Marketing, Events Marketing, & SDRs to solve workflow inefficiencies through agent-based solutions with measurable business outcomes
- Create reusable workflow templates, playbooks, and “how-to” docs so partner teams can safely self-serve common automations (with clear ownership and measurement)
- Provide hands-on technical support and troubleshooting for AI systems across teams
- Align AI chatbot systems across multiple teams (Marketing, SDR, Customer Success) to create unified prospect interaction routing
- Build intelligent routing logic that determines when and how to engage human resources in prospect interactions
- Implement tracking and analytics to measure routing effectiveness and refine human-in-the-loop triggers
- Create scalable patterns for prospect intent classification and optimal channel/resource assignment
- Define SLAs, failure modes, and fallback pathways (when routing is uncertain, when systems are down, when confidence is low)
- Instrument end-to-end funnel metrics (handoff time, qualification accuracy, meeting set rate, pipeline influence) and iterate
- Build and maintain secure, documented systems with robust PII controls, compliance protocols, and permission frameworks
- Implement company-wide standards for AI prompt engineering, version control, testing, observability, and business impact measurement
- Create internal training materials, best practices documentation, and scalable frameworks for AI tools that enable cross-functional team success
- Support ongoing AI adoption through hands-on technical assistance and system optimization
Requirements:
- 7+ years building production systems and integrations (software engineering, data/analytics engineering, business systems, or GTM engineering)
- 2+ years hands-on experience applying LLMs/AI to production workflows — not just prototypes
- Proven experience delivering AI-enabled systems or automation (0→1 or major expansions) with measurable business outcomes
- Strong in Python and JavaScript/Node.js with Git-based development workflows, code review practices, and testing discipline
- Deep familiarity with Google Cloud Platform, BigQuery, and Cloud Functions
- Hands-on experience with LLM frameworks and patterns: prompt engineering, RAG, function calling/tool use, agent orchestration, structured output parsing, and evaluation
- Fluent with AI-assisted development tools (GitHub Copilot, Cursor, Claude Code) — you use AI to build AI systems
- Experience implementing automation systems, building agent workflows, and maintaining scalable infrastructure
- Proven ability to execute, prioritize, and deliver high-ROI AI automation projects
- Strong documentation skills and ability to communicate clearly with technical and business audiences
- Experience integrating with Salesforce (or similar CRM) and at least one marketing automation platform (Customer.io / HubSpot / Marketo)
- Background working with analytics, segmentation, and personalization platforms
- Experience building multi-agent systems: agent decomposition, orchestration patterns (sequential chains, router/dispatcher, parallel fan-out), state management across handoffs
- Understanding of LLM failure modes and production mitigations: confidence thresholds, fallback logic, human escalation, cost/latency management
- Experience with systematic LLM evaluation: golden datasets, regression testing, A/B testing prompts, monitoring for drift
- Familiarity with conversational AI, chatbot development, and routing logic
- Background in B2B SaaS or GTM operations
- Active in open-source communities
- Experience with workflow orchestration platforms (n8n, Temporal, Prefect, Airflow)